├── .gitignore ├── DATAFORMAT.md ├── DATASTATEMENT.md ├── LICENSE ├── README.md └── data ├── all_crowdsourced.questions.jsonl ├── dev ├── dev.crowdsourced.jsonl ├── dev.predictions.gpt2finetuned.json ├── dev.predictions.human.jsonl └── dev.scraped.jsonl ├── omitted └── omitted.jsonl ├── test └── test.questions.jsonl └── train └── train.jsonl /.gitignore: -------------------------------------------------------------------------------- 1 | # No need for PyCharm metadata in this repo 2 | .idea 3 | 4 | # Manual Additions 5 | models 6 | scratch 7 | .ipynb_checkpoints 8 | *.ipynb 9 | 10 | # Byte-compiled / optimized / DLL files 11 | __pycache__/ 12 | *.py[cod] 13 | *$py.class 14 | 15 | # C extensions 16 | *.so 17 | 18 | # Distribution / packaging 19 | .Python 20 | build/ 21 | develop-eggs/ 22 | dist/ 23 | downloads/ 24 | eggs/ 25 | .eggs/ 26 | lib/ 27 | lib64/ 28 | parts/ 29 | sdist/ 30 | var/ 31 | wheels/ 32 | pip-wheel-metadata/ 33 | share/python-wheels/ 34 | *.egg-info/ 35 | .installed.cfg 36 | *.egg 37 | MANIFEST 38 | 39 | # PyInstaller 40 | # Usually these files are written by a python script from a template 41 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 42 | *.manifest 43 | *.spec 44 | 45 | # Installer logs 46 | pip-log.txt 47 | pip-delete-this-directory.txt 48 | 49 | # Unit test / coverage reports 50 | htmlcov/ 51 | .tox/ 52 | .nox/ 53 | .coverage 54 | .coverage.* 55 | .cache 56 | nosetests.xml 57 | coverage.xml 58 | *.cover 59 | .hypothesis/ 60 | .pytest_cache/ 61 | 62 | # Translations 63 | *.mo 64 | *.pot 65 | 66 | # Django stuff: 67 | *.log 68 | local_settings.py 69 | db.sqlite3 70 | 71 | # Flask stuff: 72 | instance/ 73 | .webassets-cache 74 | 75 | # Scrapy stuff: 76 | .scrapy 77 | 78 | # Sphinx documentation 79 | docs/_build/ 80 | 81 | # PyBuilder 82 | target/ 83 | 84 | # Jupyter Notebook 85 | .ipynb_checkpoints 86 | 87 | # IPython 88 | profile_default/ 89 | ipython_config.py 90 | 91 | # pyenv 92 | .python-version 93 | 94 | # pipenv 95 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 96 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 97 | # having no cross-platform support, pipenv may install dependencies that don’t work, or not 98 | # install all needed dependencies. 99 | #Pipfile.lock 100 | 101 | # celery beat schedule file 102 | celerybeat-schedule 103 | 104 | # SageMath parsed files 105 | *.sage.py 106 | 107 | # Environments 108 | .env 109 | .venv 110 | env/ 111 | venv/ 112 | ENV/ 113 | env.bak/ 114 | venv.bak/ 115 | 116 | # Spyder project settings 117 | .spyderproject 118 | .spyproject 119 | 120 | # Rope project settings 121 | .ropeproject 122 | 123 | # mkdocs documentation 124 | /site 125 | 126 | # mypy 127 | .mypy_cache/ 128 | .dmypy.json 129 | dmypy.json 130 | 131 | # Pyre type checker 132 | .pyre/ 133 | 134 | 135 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm 136 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 137 | 138 | # User-specific stuff 139 | .idea/**/workspace.xml 140 | .idea/**/tasks.xml 141 | .idea/**/usage.statistics.xml 142 | .idea/**/dictionaries 143 | .idea/**/shelf 144 | 145 | # Generated files 146 | .idea/**/contentModel.xml 147 | 148 | # Sensitive or high-churn files 149 | .idea/**/dataSources/ 150 | .idea/**/dataSources.ids 151 | .idea/**/dataSources.local.xml 152 | .idea/**/sqlDataSources.xml 153 | .idea/**/dynamic.xml 154 | .idea/**/uiDesigner.xml 155 | .idea/**/dbnavigator.xml 156 | 157 | # Gradle 158 | .idea/**/gradle.xml 159 | .idea/**/libraries 160 | 161 | # Gradle and Maven with auto-import 162 | # When using Gradle or Maven with auto-import, you should exclude module files, 163 | # since they will be recreated, and may cause churn. Uncomment if using 164 | # auto-import. 165 | # .idea/modules.xml 166 | # .idea/*.iml 167 | # .idea/modules 168 | 169 | # CMake 170 | cmake-build-*/ 171 | 172 | # Mongo Explorer plugin 173 | .idea/**/mongoSettings.xml 174 | 175 | # File-based project format 176 | *.iws 177 | 178 | # IntelliJ 179 | out/ 180 | 181 | # mpeltonen/sbt-idea plugin 182 | .idea_modules/ 183 | 184 | # JIRA plugin 185 | atlassian-ide-plugin.xml 186 | 187 | # Cursive Clojure plugin 188 | .idea/replstate.xml 189 | 190 | # Crashlytics plugin (for Android Studio and IntelliJ) 191 | com_crashlytics_export_strings.xml 192 | crashlytics.properties 193 | crashlytics-build.properties 194 | fabric.properties 195 | 196 | # Editor-based Rest Client 197 | .idea/httpRequests 198 | 199 | # Android studio 3.1+ serialized cache file 200 | .idea/caches/build_file_checksums.ser 201 | 202 | # Ignore these as they only make sense when not on the server 203 | .idea/webServers.xml 204 | .idea/deployment.xml 205 | 206 | # Mac OS X files 207 | .DS_Store 208 | -------------------------------------------------------------------------------- /DATAFORMAT.md: -------------------------------------------------------------------------------- 1 | # Data Format 2 | All files are in `jsonl` format. Below we describe the format expected of each line. 3 | 4 | ## Answer Cluster Data 5 | 6 | ``` 7 | { 8 | "metadata": { 9 | "id": unique id of this question, 10 | "source": source of answer strings (eg. "umass-crowdsource", url, etc.) 11 | }, 12 | "question": { 13 | "original": original string form of this question, 14 | "normalized": cleaned form of question suggested for model input 15 | }, 16 | "answers": { dictionary from answers to their counts, eg. 17 | "raw": { answer strings to counts, eg. 18 | "answer_one": 4, 19 | "answer_two": 7, 20 | ... 21 | }, 22 | "clusters": {dictionary from unique cluster ids to cluster information, eg. 23 | "r#q#.1": { 24 | "count": number of answers which correspond to this cluster, 25 | "answers": list of answers which correspond to this cluster, 26 | }, 27 | ... 28 | } 29 | "num": { 30 | "answers": sum of answer points, 31 | "clusters": number of clusters, 32 | }, 33 | } 34 | ``` 35 | 36 | ### Crowdsourced Data 37 | The "raw" answers went through additional manual cleaning (eg. filtering out nonsense answers, spell correction), and therefore the answers in "raw" and "clusters" may be different. 38 | 39 | ### Scraped Data 40 | There is only one string available per cluster. In particular, the scraped dev set is not intended for use with the generative evaluation, as the performance will be quite poor. 41 | 42 | ## Assessment Data 43 | 44 | ``` 45 | { 46 | "question_id": unique id of the associated question, 47 | "assessments": { association from answer strings to cluster ids, eg: 48 | "answer_one": "r#q#.0", 49 | "answer_two": "r#q#.4", 50 | ... 51 | } 52 | } 53 | ``` 54 | -------------------------------------------------------------------------------- /DATASTATEMENT.md: -------------------------------------------------------------------------------- 1 | 2 | # Corpus Data Statement 3 | 4 | Following [Datasheets for Datasets(Gebru et al. 2020)](https://arxiv.org/pdf/1803.09010.pdf) and [earlier NLP-specific work(Bender and Friedman 2018)](https://www.aclweb.org/anthology/Q18-1041.pdf), we want to maintain a data statement making clear the data origins and details. 5 | 6 | ## Motivation 7 | 8 | 9 | * **For what purpose was the dataset created?** This dataset is for studying computational models trained to reason about prototypical situations. It is anticipated that still would not lead to usage in a downstream task, but as a way of studying the knowledge (and biases) of prototypical situations already contained in pre-trained models. The scraped data is sourced from fan websites for a gameshow (Family Feud), and thus is optimized for entertainment rather than scientific rigor. 10 | * **Who created the dataset and on behalf of which entity:** See author list in paper. 11 | * **Who funded the creation of the dataset?:** See acknowledgments in paper. 12 | 13 | ## Composition 14 | *Regarding the scraped training and scraped-dev sets:* 15 | 16 | * **What do the instances that comprise the dataset represent?:** Each represents a survey question from the Family Feud game and reported answer clusters 17 | * **How many instances are there in total?**: 9789 instances 18 | * **Does the dataset contain all possible instances or is it a sample(not necessarily random) of instances from a larger set?**: This is a sampling from a larger set of all transcriptions of such questions on all sites. 19 | * **What data does each instance consist of?**: Each instance is a question, a set of answers, and a count associated with each answer. 20 | * **Is any information missing from individual instances?** It is unclear 21 | * **Are there recommended data splits (e.g., training, development/validation,testing)?**: Data is sorted into suggested splits, and separated in the data/ folder. 22 | * **Are there any errors, sources of noise, or redundancies in the dataset?**: All data was scraped from fan sites, and therefore prone to erroneous or incomplete additions. Redundancies were found with various automatic metrics (such as edit distance) and removed during processing, as were obviously incomplete or incorrect answer sets (e.g. when answers totaled more than 100). However, we expect there to be noise and redundancies not captured in that process. 23 | * **Is the dataset self-contained, or does it link to or otherwise rely onexternal resources**: The data is self-contained. 24 | * **Does the dataset contain data that might be considered confidential?** The data does not concern individuals and thus does not contain any information to identify persons. Crowdsourced answers do not provide any user identifiers. 25 | * **Does the dataset contain data that, if viewed directly, might be offensive, insulting, threatening, or might otherwise cause anxiety?** Not egregiously so (questions are all designed to be shown on television or replications thereof), 26 | * **Does the dataset contain data that might be considered sensitive in any way?** As the questions address prototypical/stereotypical activities, models trained on more offensive material (such as large language models) may provide offensive answers to such questions. While we had found a few questions which we worried would actually encourage models to provide offensive answers, we cannot guarantee that the data is clean of such questions. Even a perfectly innocent version of this dataset would be encouraging models to express generalizations about situations, and therefore may provoke offensive material that is contained in language models. 27 | 28 | 29 | ## Collection Process 30 | * **How was the data associated with each instance acquired?**: See paper for details. Scraped data was acquired through fan transcriptions at https://www.familyfeudinfo.com and http://familyfeudfriends.arjdesigns.com/ ; crowdsourced data was acquired with FigureEight (now Appen). 31 | * **If the dataset is a sample from a larger set, what was the sampling strategy**: Deterministic filtering was used (noted elsewhere), but no probabilistic sampling was used. 32 | * **Who was involved in the data collection process (e.g., students,crowdworkers , contractors) and how were they compensated**: Crowdworkers were used to create the evalaution dataset. Time per task was calculated and per-task cost was set to attempt to provide a living wage. 33 | * **Over what timeframe was the data collected**: Crowdsource answers were collected between Fall of 2018 and Spring of 2019. Scraped data covers question-answer pairs collected since the origin of the show in 1976. 34 | * **Annotator Demographics** The original question-answer pairs were generated by surveys of US English-speakers in a period from 1976 to present day. Crowd-sourced evaluation was constrained geographically to US English speakers but not otherwise constrained. Additional demographic data was not collected. 35 | 36 | ## Preprocessing/cleaning/labeling 37 | * **Was any preprocessing/cleaning/labeling of the data done**: Obvious typos in the crowdsourced answer set were corrected, and clearly incorrect answers removed. 38 | 39 | 40 | ## Uses 41 | * **Has the dataset been used for any tasks already?** The dataset has been used to train an interactive demo, but not deployed for other tasks. 42 | * **Is there a repository that links to any or all papers or systems thatuse the dataset?**: Such a list can be maintained here. 43 | * **What (other) tasks could the dataset be used for?** We encourage use of the dataset to study stereotypes in pre-trained language models. 44 | * **Is there anything about the composition of the dataset or the way it was collected and preprocessed/cleaned/labeled that might impact future uses?**: All original questions were written with US television audiences in mind, and therefore characterize prototypical situations from this lens. Any usages which deploy this to actually model prototypical situations globally will carry that bias. 45 | * **Are there tasks for which the dataset should not be used?**: We caution regarding free-form use of this dataset for interactive "commonsense question answering" purposes without more study of the biases and stereotypes learned by such models. 46 | 47 | ## Distribution 48 | 49 | * This dataset is distributed here via github. 50 | * **Will the dataset be distributed under a copyright or other intel-lectual property (IP) license, and/or under applicable terms of use(ToU)?**: We use CC-BY-4.0; see LICENSE . 51 | * **Have any third parties imposed IP-based or other restrictions on the data associated with the instances?**: Not at this time. 52 | 53 | ## Maintenance 54 | 55 | * **Who is supporting/hosting/maintaining the dataset?** The listed authors are maintaining/supporting the dataset. They pledge to help support issues, but cannot guarantee long-term support. 56 | * **How can the owner/curator/manager of the dataset be contacted**: See author contacts in paper, or post issues in the current repository. 57 | * **Will the dataset be updated (e.g., to correct labeling errors, add new instances, delete instances)?**: We have started an *omitted.jsonl* file of instances to be removed from the training set, and if other such instances are found that should not be used in training, we can move these to that file. Tagged releases will be used, and a history updated, for any changes to the training data. 58 | * **If others want to extend/augment/build on/contribute to the dataset, is there a mechanism for them to do so?** If interested, contact the authors of the paper. -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Attribution 4.0 International 2 | 3 | ======================================================================= 4 | 5 | Creative Commons Corporation ("Creative Commons") is not a law firm and 6 | does not provide legal services or legal advice. Distribution of 7 | Creative Commons public licenses does not create a lawyer-client or 8 | other relationship. Creative Commons makes its licenses and related 9 | information available on an "as-is" basis. Creative Commons gives no 10 | warranties regarding its licenses, any material licensed under their 11 | terms and conditions, or any related information. Creative Commons 12 | disclaims all liability for damages resulting from their use to the 13 | fullest extent possible. 14 | 15 | Using Creative Commons Public Licenses 16 | 17 | Creative Commons public licenses provide a standard set of terms and 18 | conditions that creators and other rights holders may use to share 19 | original works of authorship and other material subject to copyright 20 | and certain other rights specified in the public license below. The 21 | following considerations are for informational purposes only, are not 22 | exhaustive, and do not form part of our licenses. 23 | 24 | Considerations for licensors: Our public licenses are 25 | intended for use by those authorized to give the public 26 | permission to use material in ways otherwise restricted by 27 | copyright and certain other rights. Our licenses are 28 | irrevocable. Licensors should read and understand the terms 29 | and conditions of the license they choose before applying it. 30 | Licensors should also secure all rights necessary before 31 | applying our licenses so that the public can reuse the 32 | material as expected. Licensors should clearly mark any 33 | material not subject to the license. This includes other CC- 34 | licensed material, or material used under an exception or 35 | limitation to copyright. More considerations for licensors: 36 | wiki.creativecommons.org/Considerations_for_licensors 37 | 38 | Considerations for the public: By using one of our public 39 | licenses, a licensor grants the public permission to use the 40 | licensed material under specified terms and conditions. If 41 | the licensor's permission is not necessary for any reason--for 42 | example, because of any applicable exception or limitation to 43 | copyright--then that use is not regulated by the license. Our 44 | licenses grant only permissions under copyright and certain 45 | other rights that a licensor has authority to grant. Use of 46 | the licensed material may still be restricted for other 47 | reasons, including because others have copyright or other 48 | rights in the material. A licensor may make special requests, 49 | such as asking that all changes be marked or described. 50 | Although not required by our licenses, you are encouraged to 51 | respect those requests where reasonable. More considerations 52 | for the public: 53 | wiki.creativecommons.org/Considerations_for_licensees 54 | 55 | ======================================================================= 56 | 57 | Creative Commons Attribution 4.0 International Public License 58 | 59 | By exercising the Licensed Rights (defined below), You accept and agree 60 | to be bound by the terms and conditions of this Creative Commons 61 | Attribution 4.0 International Public License ("Public License"). To the 62 | extent this Public License may be interpreted as a contract, You are 63 | granted the Licensed Rights in consideration of Your acceptance of 64 | these terms and conditions, and the Licensor grants You such rights in 65 | consideration of benefits the Licensor receives from making the 66 | Licensed Material available under these terms and conditions. 67 | 68 | 69 | Section 1 -- Definitions. 70 | 71 | a. Adapted Material means material subject to Copyright and Similar 72 | Rights that is derived from or based upon the Licensed Material 73 | and in which the Licensed Material is translated, altered, 74 | arranged, transformed, or otherwise modified in a manner requiring 75 | permission under the Copyright and Similar Rights held by the 76 | Licensor. For purposes of this Public License, where the Licensed 77 | Material is a musical work, performance, or sound recording, 78 | Adapted Material is always produced where the Licensed Material is 79 | synched in timed relation with a moving image. 80 | 81 | b. Adapter's License means the license You apply to Your Copyright 82 | and Similar Rights in Your contributions to Adapted Material in 83 | accordance with the terms and conditions of this Public License. 84 | 85 | c. Copyright and Similar Rights means copyright and/or similar rights 86 | closely related to copyright including, without limitation, 87 | performance, broadcast, sound recording, and Sui Generis Database 88 | Rights, without regard to how the rights are labeled or 89 | categorized. For purposes of this Public License, the rights 90 | specified in Section 2(b)(1)-(2) are not Copyright and Similar 91 | Rights. 92 | 93 | d. Effective Technological Measures means those measures that, in the 94 | absence of proper authority, may not be circumvented under laws 95 | fulfilling obligations under Article 11 of the WIPO Copyright 96 | Treaty adopted on December 20, 1996, and/or similar international 97 | agreements. 98 | 99 | e. Exceptions and Limitations means fair use, fair dealing, and/or 100 | any other exception or limitation to Copyright and Similar Rights 101 | that applies to Your use of the Licensed Material. 102 | 103 | f. Licensed Material means the artistic or literary work, database, 104 | or other material to which the Licensor applied this Public 105 | License. 106 | 107 | g. Licensed Rights means the rights granted to You subject to the 108 | terms and conditions of this Public License, which are limited to 109 | all Copyright and Similar Rights that apply to Your use of the 110 | Licensed Material and that the Licensor has authority to license. 111 | 112 | h. Licensor means the individual(s) or entity(ies) granting rights 113 | under this Public License. 114 | 115 | i. Share means to provide material to the public by any means or 116 | process that requires permission under the Licensed Rights, such 117 | as reproduction, public display, public performance, distribution, 118 | dissemination, communication, or importation, and to make material 119 | available to the public including in ways that members of the 120 | public may access the material from a place and at a time 121 | individually chosen by them. 122 | 123 | j. Sui Generis Database Rights means rights other than copyright 124 | resulting from Directive 96/9/EC of the European Parliament and of 125 | the Council of 11 March 1996 on the legal protection of databases, 126 | as amended and/or succeeded, as well as other essentially 127 | equivalent rights anywhere in the world. 128 | 129 | k. You means the individual or entity exercising the Licensed Rights 130 | under this Public License. Your has a corresponding meaning. 131 | 132 | 133 | Section 2 -- Scope. 134 | 135 | a. License grant. 136 | 137 | 1. Subject to the terms and conditions of this Public License, 138 | the Licensor hereby grants You a worldwide, royalty-free, 139 | non-sublicensable, non-exclusive, irrevocable license to 140 | exercise the Licensed Rights in the Licensed Material to: 141 | 142 | a. reproduce and Share the Licensed Material, in whole or 143 | in part; and 144 | 145 | b. produce, reproduce, and Share Adapted Material. 146 | 147 | 2. Exceptions and Limitations. For the avoidance of doubt, where 148 | Exceptions and Limitations apply to Your use, this Public 149 | License does not apply, and You do not need to comply with 150 | its terms and conditions. 151 | 152 | 3. Term. The term of this Public License is specified in Section 153 | 6(a). 154 | 155 | 4. Media and formats; technical modifications allowed. The 156 | Licensor authorizes You to exercise the Licensed Rights in 157 | all media and formats whether now known or hereafter created, 158 | and to make technical modifications necessary to do so. The 159 | Licensor waives and/or agrees not to assert any right or 160 | authority to forbid You from making technical modifications 161 | necessary to exercise the Licensed Rights, including 162 | technical modifications necessary to circumvent Effective 163 | Technological Measures. For purposes of this Public License, 164 | simply making modifications authorized by this Section 2(a) 165 | (4) never produces Adapted Material. 166 | 167 | 5. Downstream recipients. 168 | 169 | a. Offer from the Licensor -- Licensed Material. Every 170 | recipient of the Licensed Material automatically 171 | receives an offer from the Licensor to exercise the 172 | Licensed Rights under the terms and conditions of this 173 | Public License. 174 | 175 | b. No downstream restrictions. You may not offer or impose 176 | any additional or different terms or conditions on, or 177 | apply any Effective Technological Measures to, the 178 | Licensed Material if doing so restricts exercise of the 179 | Licensed Rights by any recipient of the Licensed 180 | Material. 181 | 182 | 6. No endorsement. Nothing in this Public License constitutes or 183 | may be construed as permission to assert or imply that You 184 | are, or that Your use of the Licensed Material is, connected 185 | with, or sponsored, endorsed, or granted official status by, 186 | the Licensor or others designated to receive attribution as 187 | provided in Section 3(a)(1)(A)(i). 188 | 189 | b. Other rights. 190 | 191 | 1. Moral rights, such as the right of integrity, are not 192 | licensed under this Public License, nor are publicity, 193 | privacy, and/or other similar personality rights; however, to 194 | the extent possible, the Licensor waives and/or agrees not to 195 | assert any such rights held by the Licensor to the limited 196 | extent necessary to allow You to exercise the Licensed 197 | Rights, but not otherwise. 198 | 199 | 2. Patent and trademark rights are not licensed under this 200 | Public License. 201 | 202 | 3. To the extent possible, the Licensor waives any right to 203 | collect royalties from You for the exercise of the Licensed 204 | Rights, whether directly or through a collecting society 205 | under any voluntary or waivable statutory or compulsory 206 | licensing scheme. In all other cases the Licensor expressly 207 | reserves any right to collect such royalties. 208 | 209 | 210 | Section 3 -- License Conditions. 211 | 212 | Your exercise of the Licensed Rights is expressly made subject to the 213 | following conditions. 214 | 215 | a. Attribution. 216 | 217 | 1. If You Share the Licensed Material (including in modified 218 | form), You must: 219 | 220 | a. retain the following if it is supplied by the Licensor 221 | with the Licensed Material: 222 | 223 | i. identification of the creator(s) of the Licensed 224 | Material and any others designated to receive 225 | attribution, in any reasonable manner requested by 226 | the Licensor (including by pseudonym if 227 | designated); 228 | 229 | ii. a copyright notice; 230 | 231 | iii. a notice that refers to this Public License; 232 | 233 | iv. a notice that refers to the disclaimer of 234 | warranties; 235 | 236 | v. a URI or hyperlink to the Licensed Material to the 237 | extent reasonably practicable; 238 | 239 | b. indicate if You modified the Licensed Material and 240 | retain an indication of any previous modifications; and 241 | 242 | c. indicate the Licensed Material is licensed under this 243 | Public License, and include the text of, or the URI or 244 | hyperlink to, this Public License. 245 | 246 | 2. You may satisfy the conditions in Section 3(a)(1) in any 247 | reasonable manner based on the medium, means, and context in 248 | which You Share the Licensed Material. For example, it may be 249 | reasonable to satisfy the conditions by providing a URI or 250 | hyperlink to a resource that includes the required 251 | information. 252 | 253 | 3. If requested by the Licensor, You must remove any of the 254 | information required by Section 3(a)(1)(A) to the extent 255 | reasonably practicable. 256 | 257 | 4. If You Share Adapted Material You produce, the Adapter's 258 | License You apply must not prevent recipients of the Adapted 259 | Material from complying with this Public License. 260 | 261 | 262 | Section 4 -- Sui Generis Database Rights. 263 | 264 | Where the Licensed Rights include Sui Generis Database Rights that 265 | apply to Your use of the Licensed Material: 266 | 267 | a. for the avoidance of doubt, Section 2(a)(1) grants You the right 268 | to extract, reuse, reproduce, and Share all or a substantial 269 | portion of the contents of the database; 270 | 271 | b. if You include all or a substantial portion of the database 272 | contents in a database in which You have Sui Generis Database 273 | Rights, then the database in which You have Sui Generis Database 274 | Rights (but not its individual contents) is Adapted Material; and 275 | 276 | c. You must comply with the conditions in Section 3(a) if You Share 277 | all or a substantial portion of the contents of the database. 278 | 279 | For the avoidance of doubt, this Section 4 supplements and does not 280 | replace Your obligations under this Public License where the Licensed 281 | Rights include other Copyright and Similar Rights. 282 | 283 | 284 | Section 5 -- Disclaimer of Warranties and Limitation of Liability. 285 | 286 | a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE 287 | EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS 288 | AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF 289 | ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS, 290 | IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION, 291 | WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR 292 | PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS, 293 | ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT 294 | KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT 295 | ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU. 296 | 297 | b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE 298 | TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION, 299 | NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT, 300 | INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES, 301 | COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR 302 | USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN 303 | ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR 304 | DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR 305 | IN PART, THIS LIMITATION MAY NOT APPLY TO YOU. 306 | 307 | c. The disclaimer of warranties and limitation of liability provided 308 | above shall be interpreted in a manner that, to the extent 309 | possible, most closely approximates an absolute disclaimer and 310 | waiver of all liability. 311 | 312 | 313 | Section 6 -- Term and Termination. 314 | 315 | a. This Public License applies for the term of the Copyright and 316 | Similar Rights licensed here. However, if You fail to comply with 317 | this Public License, then Your rights under this Public License 318 | terminate automatically. 319 | 320 | b. Where Your right to use the Licensed Material has terminated under 321 | Section 6(a), it reinstates: 322 | 323 | 1. automatically as of the date the violation is cured, provided 324 | it is cured within 30 days of Your discovery of the 325 | violation; or 326 | 327 | 2. upon express reinstatement by the Licensor. 328 | 329 | For the avoidance of doubt, this Section 6(b) does not affect any 330 | right the Licensor may have to seek remedies for Your violations 331 | of this Public License. 332 | 333 | c. For the avoidance of doubt, the Licensor may also offer the 334 | Licensed Material under separate terms or conditions or stop 335 | distributing the Licensed Material at any time; however, doing so 336 | will not terminate this Public License. 337 | 338 | d. Sections 1, 5, 6, 7, and 8 survive termination of this Public 339 | License. 340 | 341 | 342 | Section 7 -- Other Terms and Conditions. 343 | 344 | a. The Licensor shall not be bound by any additional or different 345 | terms or conditions communicated by You unless expressly agreed. 346 | 347 | b. Any arrangements, understandings, or agreements regarding the 348 | Licensed Material not stated herein are separate from and 349 | independent of the terms and conditions of this Public License. 350 | 351 | 352 | Section 8 -- Interpretation. 353 | 354 | a. For the avoidance of doubt, this Public License does not, and 355 | shall not be interpreted to, reduce, limit, restrict, or impose 356 | conditions on any use of the Licensed Material that could lawfully 357 | be made without permission under this Public License. 358 | 359 | b. To the extent possible, if any provision of this Public License is 360 | deemed unenforceable, it shall be automatically reformed to the 361 | minimum extent necessary to make it enforceable. If the provision 362 | cannot be reformed, it shall be severed from this Public License 363 | without affecting the enforceability of the remaining terms and 364 | conditions. 365 | 366 | c. No term or condition of this Public License will be waived and no 367 | failure to comply consented to unless expressly agreed to by the 368 | Licensor. 369 | 370 | d. Nothing in this Public License constitutes or may be interpreted 371 | as a limitation upon, or waiver of, any privileges and immunities 372 | that apply to the Licensor or You, including from the legal 373 | processes of any jurisdiction or authority. 374 | 375 | 376 | ======================================================================= 377 | 378 | Creative Commons is not a party to its public licenses. 379 | Notwithstanding, Creative Commons may elect to apply one of its public 380 | licenses to material it publishes and in those instances will be 381 | considered the “Licensor.” The text of the Creative Commons public 382 | licenses is dedicated to the public domain under the CC0 Public Domain 383 | Dedication. Except for the limited purpose of indicating that material 384 | is shared under a Creative Commons public license or as otherwise 385 | permitted by the Creative Commons policies published at 386 | creativecommons.org/policies, Creative Commons does not authorize the 387 | use of the trademark "Creative Commons" or any other trademark or logo 388 | of Creative Commons without its prior written consent including, 389 | without limitation, in connection with any unauthorized modifications 390 | to any of its public licenses or any other arrangements, 391 | understandings, or agreements concerning use of licensed material. For 392 | the avoidance of doubt, this paragraph does not form part of the public 393 | licenses. 394 | 395 | Creative Commons may be contacted at creativecommons.org. 396 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # ProtoQA Dataset 2 | 3 | This repository contains the dataset for ProtoQA ("Family Feud"). See [the paper](https://arxiv.org/abs/2005.00771) for details on dataset creation. 4 | 5 | ## Data Files: 6 | Each line is a json dictionary, in which: 7 | * **question** contains the question (in original and a normalized form) 8 | * **answers** (where available) contains: 9 | * **raw** original answers provided by survey respondents (when available) with their counts 10 | * **clusters** which include the score for each cluster and the strings included in that cluster 11 | 12 | For a full description of the data format, see [DATAFORMAT.md](DATAFORMAT.md). 13 | 14 | 15 | ## File organization: 16 | 17 | * **data/train/train.jsonl**: 8781 instances for training or fine-tuning scraped from Family Feud fan sites (see paper). Scraped data has answer clusters with sizes, but only has a single string per cluster (corresponding to the original cluster name. 18 | * **data/dev/dev.scraped.jsonl**: 979 instances sampled from the same Family Feud data, for use in model validation and development. 19 | * **data/dev/dev.crowdsourced.jsonl**: 51 questions collected with exhaustive answer collection and manual clustering, matching the details of the eval test set (roughly 100 human answers per question). 20 | * **data/test/test.questions.jsonl** 102 questions for evaluation. (Note that the test set contains questions only.) 21 | 22 | 23 | ## Notes: 24 | This repository contains a [data statement](DATASTATEMENT.md) (based on [Datasheets for Datasets (Gebru et al. 2020)](https://arxiv.org/pdf/1803.09010.pdf) and [earlier NLP-specific work (Bender and Friedman 2018)](https://www.aclweb.org/anthology/Q18-1041.pdf)) to provide transparency in data use and encourage others to do so. This is a preliminary version of the statement; please post issues in the repository or contact the authors if you have questions regarding the data details or suggestions regarding the dataset use. 25 | -------------------------------------------------------------------------------- /data/all_crowdsourced.questions.jsonl: -------------------------------------------------------------------------------- 1 | {"metadata": {"id": "r1q1", "source": "umass-crowdsource"}, "question": {"original": "Name something that is hard to guess about a person you are just meeting.", "normalized": "name something that is hard to guess about a person you are just meeting."}} 2 | {"metadata": {"id": "r1q2", "source": "umass-crowdsource"}, "question": {"original": "What could be some of the reasons you could be called to your kid's school?", "normalized": "what could be some of the reasons you could be called to your kid's school?"}} 3 | {"metadata": {"id": "r1q3", "source": "umass-crowdsource"}, "question": {"original": "Name something a monk probably would not own.", "normalized": "name something a monk probably would not own."}} 4 | {"metadata": {"id": "r1q5", "source": "umass-crowdsource"}, "question": {"original": "Name something that people usually do before they leave the house for work?", "normalized": "name something that people usually do before they leave the house for work?"}} 5 | {"metadata": {"id": "r1q6", "source": "umass-crowdsource"}, "question": {"original": "Name something you are likely making if you buy milk, eggs, sugar and cream.", "normalized": "name something you are likely making if you buy milk, eggs, sugar and cream."}} 6 | {"metadata": {"id": "r1q7", "source": "umass-crowdsource"}, "question": {"original": "Name a vegetable that is about as big as your head.", "normalized": "name a vegetable that is about as big as your head."}} 7 | {"metadata": {"id": "r1q8", "source": "umass-crowdsource"}, "question": {"original": "Name a luxury people give up while traveling.", "normalized": "name a luxury people give up while traveling."}} 8 | {"metadata": {"id": "r1q9", "source": "umass-crowdsource"}, "question": {"original": "Name a sport that requires a lot of equipment.", "normalized": "name a sport that requires a lot of equipment."}} 9 | {"metadata": {"id": "r1q10", "source": "umass-crowdsource"}, "question": {"original": "Name something people might turn their garage into.", "normalized": "name something people might turn their garage into."}} 10 | {"metadata": {"id": "r1q11", "source": "umass-crowdsource"}, "question": {"original": "Name something that keeps children safe.", "normalized": "name something that keeps children safe."}} 11 | {"metadata": {"id": "r1q12", "source": "umass-crowdsource"}, "question": {"original": "Name somewhere that has a pole.", "normalized": "name somewhere that has a pole."}} 12 | {"metadata": {"id": "r1q14", "source": "umass-crowdsource"}, "question": {"original": "Name something that gets caught in your hair.", "normalized": "name something that gets caught in your hair."}} 13 | {"metadata": {"id": "r1q16", "source": "umass-crowdsource"}, "question": {"original": "Name a piece of equipment that you are likely to find at your office and not at home?", "normalized": "name a piece of equipment that you are likely to find at your office and not at home?"}} 14 | {"metadata": {"id": "r1q17", "source": "umass-crowdsource"}, "question": {"original": "Name something that an athelete would not keep in her refrigerator.", "normalized": "name something that an athelete would not keep in her refrigerator."}} 15 | {"metadata": {"id": "r1q18", "source": "umass-crowdsource"}, "question": {"original": "Name an item of clothing that you would not lend to someone.", "normalized": "name an item of clothing that you would not lend to someone."}} 16 | {"metadata": {"id": "r1q19", "source": "umass-crowdsource"}, "question": {"original": "Name a cause you are likely to donate to.", "normalized": "name a cause you are likely to donate to."}} 17 | {"metadata": {"id": "r1q20", "source": "umass-crowdsource"}, "question": {"original": "Name something they give away free to attract customers to a store.", "normalized": "name something they give away free to attract customers to a store."}} 18 | {"metadata": {"id": "r2q3", "source": "umass-crowdsource"}, "question": {"original": "Name a popular dish made with cheese.", "normalized": "name a popular dish made with cheese."}} 19 | {"metadata": {"id": "r2q4", "source": "umass-crowdsource"}, "question": {"original": "Name a reason why someone would wear gloves.", "normalized": "name a reason why someone would wear gloves."}} 20 | {"metadata": {"id": "r2q5", "source": "umass-crowdsource"}, "question": {"original": "Name a sign that two people are friends.", "normalized": "name a sign that two people are friends."}} 21 | {"metadata": {"id": "r2q6", "source": "umass-crowdsource"}, "question": {"original": "Name something around the house that\u2019s often replaced.", "normalized": "name something around the house that\u2019s often replaced."}} 22 | {"metadata": {"id": "r2q7", "source": "umass-crowdsource"}, "question": {"original": "Name something parents tell their kids not to do", "normalized": "name something parents tell their kids not to do"}} 23 | {"metadata": {"id": "r2q8", "source": "umass-crowdsource"}, "question": {"original": "Name a job where you have to be awake at night.", "normalized": "name a job where you have to be awake at night."}} 24 | {"metadata": {"id": "r2q9", "source": "umass-crowdsource"}, "question": {"original": "Name a complaint people have about their gym instructors.", "normalized": "name a complaint people have about their gym instructors."}} 25 | {"metadata": {"id": "r2q10", "source": "umass-crowdsource"}, "question": {"original": "Name something parents would criticize their children for having.", "normalized": "name something parents would criticize their children for having."}} 26 | {"metadata": {"id": "r2q11", "source": "umass-crowdsource"}, "question": {"original": "Name something people do with close friends that they wouldn't do with a stranger.", "normalized": "name something people do with close friends that they wouldn't do with a stranger."}} 27 | {"metadata": {"id": "r2q12", "source": "umass-crowdsource"}, "question": {"original": "Name something people might buy for a house that they would not buy for an apartment.", "normalized": "name something people might buy for a house that they would not buy for an apartment."}} 28 | {"metadata": {"id": "r2q14", "source": "umass-crowdsource"}, "question": {"original": "Instead of going to college, name something a person might do after high school.", "normalized": "instead of going to college, name something a person might do after high school."}} 29 | {"metadata": {"id": "r2q15", "source": "umass-crowdsource"}, "question": {"original": "Name something that people often remember for a long time, even when they get old.", "normalized": "name something that people often remember for a long time, even when they get old."}} 30 | {"metadata": {"id": "r2q18", "source": "umass-crowdsource"}, "question": {"original": "Name something that happens in real life but never makes the news.", "normalized": "name something that happens in real life but never makes the news."}} 31 | {"metadata": {"id": "r2q19", "source": "umass-crowdsource"}, "question": {"original": "Name something specific that gets jumped.", "normalized": "name something specific that gets jumped."}} 32 | {"metadata": {"id": "r2q20", "source": "umass-crowdsource"}, "question": {"original": "Name something at the store you would find on the same aisle as cereal.", "normalized": "name something at the store you would find on the same aisle as cereal."}} 33 | {"metadata": {"id": "r2q21", "source": "umass-crowdsource"}, "question": {"original": "Name something you need to make a pizza.", "normalized": "name something you need to make a pizza."}} 34 | {"metadata": {"id": "r2q23", "source": "umass-crowdsource"}, "question": {"original": "Name a word you hear almost every coach say at a high school football game.", "normalized": "name a word you hear almost every coach say at a high school football game."}} 35 | {"metadata": {"id": "r2q25", "source": "umass-crowdsource"}, "question": {"original": "Name a reason why a person might prefer to own a cat over a dog.", "normalized": "name a reason why a person might prefer to own a cat over a dog."}} 36 | {"metadata": {"id": "r2q26", "source": "umass-crowdsource"}, "question": {"original": "Name an animal that someone might teach to do tricks.", "normalized": "name an animal that someone might teach to do tricks."}} 37 | {"metadata": {"id": "r2q27", "source": "umass-crowdsource"}, "question": {"original": "Name something people do while getting checked by their dentist.", "normalized": "name something people do while getting checked by their dentist."}} 38 | {"metadata": {"id": "r2q30", "source": "umass-crowdsource"}, "question": {"original": "Name a reason why someone might have to pull off to the side of the road while driving.", "normalized": "name a reason why someone might have to pull off to the side of the road while driving."}} 39 | {"metadata": {"id": "r2q31", "source": "umass-crowdsource"}, "question": {"original": "Besides birds, name a pet people keep in an cage.", "normalized": "besides birds, name a pet people keep in an cage."}} 40 | {"metadata": {"id": "r2q32", "source": "umass-crowdsource"}, "question": {"original": "Name a reason why a child may not want to be friends with another child.", "normalized": "name a reason why a child may not want to be friends with another child."}} 41 | {"metadata": {"id": "r2q35", "source": "umass-crowdsource"}, "question": {"original": "Name a job which has a lot of power and influence which is not part of the government.", "normalized": "name a job which has a lot of power and influence which is not part of the government."}} 42 | {"metadata": {"id": "r2q37", "source": "umass-crowdsource"}, "question": {"original": "Name something that would cause you to stop speaking to your best friend.", "normalized": "name something that would cause you to stop speaking to your best friend."}} 43 | {"metadata": {"id": "r2q38", "source": "umass-crowdsource"}, "question": {"original": "Name something people buy that lasts a long time.", "normalized": "name something people buy that lasts a long time."}} 44 | {"metadata": {"id": "r2q39", "source": "umass-crowdsource"}, "question": {"original": "Name an activity that's often depicted in movies though people seldom do it in real life.", "normalized": "name an activity that's often depicted in movies though people seldom do it in real life."}} 45 | {"metadata": {"id": "r2q40", "source": "umass-crowdsource"}, "question": {"original": "Name something scary that people are no longer scared of when they get older.", "normalized": "name something scary that people are no longer scared of when they get older."}} 46 | {"metadata": {"id": "r2q42", "source": "umass-crowdsource"}, "question": {"original": "Name something that would make someone change their return flight.", "normalized": "name something that would make someone change their return flight."}} 47 | {"metadata": {"id": "r2q43", "source": "umass-crowdsource"}, "question": {"original": "Name something a delivery person might see in someone's yard that would prevent them from delivering a package.", "normalized": "name something a delivery person might see in someone's yard that would prevent them from delivering a package."}} 48 | {"metadata": {"id": "r2q44", "source": "umass-crowdsource"}, "question": {"original": "Tell me something a poor person might have which is smaller than most peoples.", "normalized": "tell me something a poor person might have which is smaller than most peoples."}} 49 | {"metadata": {"id": "r2q45", "source": "umass-crowdsource"}, "question": {"original": "Name something in your life that could cause you to lose weight.", "normalized": "name something in your life that could cause you to lose weight."}} 50 | {"metadata": {"id": "r2q46", "source": "umass-crowdsource"}, "question": {"original": "Name a reason why you might give a waiter a good tip.", "normalized": "name a reason why you might give a waiter a good tip."}} 51 | {"metadata": {"id": "r2q47", "source": "umass-crowdsource"}, "question": {"original": "Name something that you might break on purpose.", "normalized": "name something that you might break on purpose."}} 52 | {"metadata": {"id": "r2q49", "source": "umass-crowdsource"}, "question": {"original": "Name a place where you might have a long conversation with someone who works there.", "normalized": "name a place where you might have a long conversation with someone who works there."}} 53 | {"metadata": {"id": "r1q4", "source": "umass-crowdsource"}, "question": {"original": "Name a complaint people have about their parents.", "normalized": "name a complaint people have about their parents."}} 54 | {"metadata": {"id": "r1q13", "source": "umass-crowdsource"}, "question": {"original": "Name a hobby better suited for city living than country living.", "normalized": "name a hobby better suited for city living than country living."}} 55 | {"metadata": {"id": "r1q15", "source": "umass-crowdsource"}, "question": {"original": "Name a sport that takes a long time to play.", "normalized": "name a sport that takes a long time to play."}} 56 | {"metadata": {"id": "r2q2", "source": "umass-crowdsource"}, "question": {"original": "Name something babies probably cry about.", "normalized": "name something babies probably cry about."}} 57 | {"metadata": {"id": "r2q16", "source": "umass-crowdsource"}, "question": {"original": "Name a characteristic commonly associated with professors.", "normalized": "name a characteristic commonly associated with professors."}} 58 | {"metadata": {"id": "r2q22", "source": "umass-crowdsource"}, "question": {"original": "Name something a small-town politician would do while campaigning.", "normalized": "name something a small-town politician would do while campaigning."}} 59 | {"metadata": {"id": "r2q29", "source": "umass-crowdsource"}, "question": {"original": "Name something parents are proud of their children for.", "normalized": "name something parents are proud of their children for."}} 60 | {"metadata": {"id": "r2q33", "source": "umass-crowdsource"}, "question": {"original": "Name something you would need if you were lost in Antarctica.", "normalized": "name something you would need if you were lost in antarctica."}} 61 | {"metadata": {"id": "r2q36", "source": "umass-crowdsource"}, "question": {"original": "Name something annoying a person might do at fast food restaurant when there's a long line behind them.", "normalized": "name something annoying a person might do at fast food restaurant when there's a long line behind them."}} 62 | {"metadata": {"id": "r2q41", "source": "umass-crowdsource"}, "question": {"original": "Name something a boss might do and then tell their employees not to do.", "normalized": "name something a boss might do and then tell their employees not to do."}} 63 | {"metadata": {"id": "r2q48", "source": "umass-crowdsource"}, "question": {"original": "Name something you would find in someone's car which is not part of the car itself.", "normalized": "name something you would find in someone's car which is not part of the car itself."}} 64 | {"metadata": {"id": "r2q50", "source": "umass-crowdsource"}, "question": {"original": "Name something you might forget at a hotel room.", "normalized": "name something you might forget at a hotel room."}} 65 | {"metadata": {"id": "r3q1", "source": "umass-crowdsource"}, "question": {"original": "Name a reason someone might not want to stay in the hotel they booked", "normalized": "name a reason someone might not want to stay in the hotel they booked"}} 66 | {"metadata": {"id": "r3q3", "source": "umass-crowdsource"}, "question": {"original": "Name something that a person usually does after they get home after running outside in the sun?", "normalized": "name something that a person usually does after they get home after running outside in the sun?"}} 67 | {"metadata": {"id": "r3q4", "source": "umass-crowdsource"}, "question": {"original": "Name a reason why a restaurant might be very empty", "normalized": "name a reason why a restaurant might be very empty"}} 68 | {"metadata": {"id": "r3q6", "source": "umass-crowdsource"}, "question": {"original": "Name a dish that is very messy to eat", "normalized": "name a dish that is very messy to eat"}} 69 | {"metadata": {"id": "r3q7", "source": "umass-crowdsource"}, "question": {"original": "Name something on which kids might need their parents signature", "normalized": "name something on which kids might need their parents signature"}} 70 | {"metadata": {"id": "r3q8", "source": "umass-crowdsource"}, "question": {"original": "Name a body part that might hurt when a person wears a high heeled shoe?", "normalized": "name a body part that might hurt when a person wears a high heeled shoe?"}} 71 | {"metadata": {"id": "r3q9", "source": "umass-crowdsource"}, "question": {"original": "Apart from their coach, name someone who plays an important role in an athletes life?", "normalized": "apart from their coach, name someone who plays an important role in an athletes life?"}} 72 | {"metadata": {"id": "r3q11", "source": "umass-crowdsource"}, "question": {"original": "Name something you do while eating dinner at home that you can't do in a restaurant.", "normalized": "name something you do while eating dinner at home that you can't do in a restaurant."}} 73 | {"metadata": {"id": "r3q12", "source": "umass-crowdsource"}, "question": {"original": "Name something people do to wake themselves up if they are tired.", "normalized": "name something people do to wake themselves up if they are tired."}} 74 | {"metadata": {"id": "r3q13", "source": "umass-crowdsource"}, "question": {"original": "Name something many people are happy to do alone.", "normalized": "name something many people are happy to do alone."}} 75 | {"metadata": {"id": "r3q14", "source": "umass-crowdsource"}, "question": {"original": "Name a job where your clothes get really wet.", "normalized": "name a job where your clothes get really wet."}} 76 | {"metadata": {"id": "r3q15", "source": "umass-crowdsource"}, "question": {"original": "Name a reason why people may not return clothes they bought which don't fit them.", "normalized": "name a reason why people may not return clothes they bought which don't fit them."}} 77 | {"metadata": {"id": "r3q16", "source": "umass-crowdsource"}, "question": {"original": "Name a mode of transportation that is easy to use while caring for children", "normalized": "name a mode of transportation that is easy to use while caring for children"}} 78 | {"metadata": {"id": "r3q17", "source": "umass-crowdsource"}, "question": {"original": "Name something their parents do which children brag about.", "normalized": "name something their parents do which children brag about."}} 79 | {"metadata": {"id": "r3q19", "source": "umass-crowdsource"}, "question": {"original": "Name something that when you forget to carry might prevent you from entering a bar", "normalized": "name something that when you forget to carry might prevent you from entering a bar"}} 80 | {"metadata": {"id": "r3q20", "source": "umass-crowdsource"}, "question": {"original": "Name a reason a person would be eager to change careers", "normalized": "name a reason a person would be eager to change careers"}} 81 | {"metadata": {"id": "r3q21", "source": "umass-crowdsource"}, "question": {"original": "Name something you might need if you own a car", "normalized": "name something you might need if you own a car"}} 82 | {"metadata": {"id": "r3q22", "source": "umass-crowdsource"}, "question": {"original": "Name something a policecar has which a regular car does not", "normalized": "name something a policecar has which a regular car does not"}} 83 | {"metadata": {"id": "r3q23", "source": "umass-crowdsource"}, "question": {"original": "Name a food you could still eat if you had a queasy stomach", "normalized": "name a food you could still eat if you had a queasy stomach"}} 84 | {"metadata": {"id": "r3q24", "source": "umass-crowdsource"}, "question": {"original": "Name a serious situation where you might prepare a speech", "normalized": "name a serious situation where you might prepare a speech"}} 85 | {"metadata": {"id": "r3q25", "source": "umass-crowdsource"}, "question": {"original": "Name an activity a driver might engage in which could cause an accident", "normalized": "name an activity a driver might engage in which could cause an accident"}} 86 | {"metadata": {"id": "r3q26", "source": "umass-crowdsource"}, "question": {"original": "Name something you wouldn't touch without washing your hands first.", "normalized": "name something you wouldn't touch without washing your hands first."}} 87 | {"metadata": {"id": "r3q27", "source": "umass-crowdsource"}, "question": {"original": "Name something people do on airplanes if they are scared.", "normalized": "name something people do on airplanes if they are scared."}} 88 | {"metadata": {"id": "r3q28", "source": "umass-crowdsource"}, "question": {"original": "Name an activity where it would be dangerous to wear headphones.", "normalized": "name an activity where it would be dangerous to wear headphones."}} 89 | {"metadata": {"id": "r3q29", "source": "umass-crowdsource"}, "question": {"original": "Name something that a detective might look for at a burglary.", "normalized": "name something that a detective might look for at a burglary."}} 90 | {"metadata": {"id": "r3q30", "source": "umass-crowdsource"}, "question": {"original": "Name something that would make a driver honk their horn.", "normalized": "name something that would make a driver honk their horn."}} 91 | {"metadata": {"id": "r3q32", "source": "umass-crowdsource"}, "question": {"original": "Other than being stopped by a cop, name a reason why someone might have to pull off to the side of the road while driving.", "normalized": "other than being stopped by a cop, name a reason why someone might have to pull off to the side of the road while driving."}} 92 | {"metadata": {"id": "r3q33", "source": "umass-crowdsource"}, "question": {"original": "Besides buying one, name a way someone might be able to get a house.", "normalized": "besides buying one, name a way someone might be able to get a house."}} 93 | {"metadata": {"id": "r3q34", "source": "umass-crowdsource"}, "question": {"original": "Name a reason for people to go into graduate school", "normalized": "name a reason for people to go into graduate school"}} 94 | {"metadata": {"id": "r3q35", "source": "umass-crowdsource"}, "question": {"original": "Name a food which usually has low-calorie", "normalized": "name a food which usually has low-calorie"}} 95 | {"metadata": {"id": "r3q36", "source": "umass-crowdsource"}, "question": {"original": "Name a reason people prefer to live in big cities rather than small towns.", "normalized": "name a reason people prefer to live in big cities rather than small towns."}} 96 | {"metadata": {"id": "r3q37", "source": "umass-crowdsource"}, "question": {"original": "Name an accessory that might be given to you if you go join a cooking class?", "normalized": "name an accessory that might be given to you if you go join a cooking class?"}} 97 | {"metadata": {"id": "r3q38", "source": "umass-crowdsource"}, "question": {"original": "Name a feeling that you might experience after having a heavy meal in the afternoon", "normalized": "name a feeling that you might experience after having a heavy meal in the afternoon"}} 98 | {"metadata": {"id": "r3q39", "source": "umass-crowdsource"}, "question": {"original": "Name a place that you can make new friends as an adult.", "normalized": "name a place that you can make new friends as an adult."}} 99 | {"metadata": {"id": "r3q40", "source": "umass-crowdsource"}, "question": {"original": "Name something you'd be embarassed to have in the car if you got pulled over.", "normalized": "name something you'd be embarassed to have in the car if you got pulled over."}} 100 | {"metadata": {"id": "r3q41", "source": "umass-crowdsource"}, "question": {"original": "Name a place you might have to wait in line.", "normalized": "name a place you might have to wait in line."}} 101 | {"metadata": {"id": "r3q42", "source": "umass-crowdsource"}, "question": {"original": "Name something you might buy to show your support for a sports team", "normalized": "name something you might buy to show your support for a sports team"}} 102 | {"metadata": {"id": "r3q43", "source": "umass-crowdsource"}, "question": {"original": "Name an occupation in which you'd be at greater risk of getting burned", "normalized": "name an occupation in which you'd be at greater risk of getting burned"}} 103 | {"metadata": {"id": "r3q45", "source": "umass-crowdsource"}, "question": {"original": "Name something a queen has but most woman dont have", "normalized": "name something a queen has but most woman dont have"}} 104 | {"metadata": {"id": "r3q46", "source": "umass-crowdsource"}, "question": {"original": "Name an occupation where you might need a car", "normalized": "name an occupation where you might need a car"}} 105 | {"metadata": {"id": "r3q47", "source": "umass-crowdsource"}, "question": {"original": "If your pizza was delivered very late what would be a possible reason for that.", "normalized": "if your pizza was delivered very late what would be a possible reason for that."}} 106 | {"metadata": {"id": "r3q48", "source": "umass-crowdsource"}, "question": {"original": "Name something people should not do when they are angry", "normalized": "name something people should not do when they are angry"}} 107 | {"metadata": {"id": "r3q49", "source": "umass-crowdsource"}, "question": {"original": "Name something people do ahead of time when family is coming to stay", "normalized": "name something people do ahead of time when family is coming to stay"}} 108 | {"metadata": {"id": "r3q50", "source": "umass-crowdsource"}, "question": {"original": "Name an event where someone might meet a lot of new people.", "normalized": "name an event where someone might meet a lot of new people."}} 109 | {"metadata": {"id": "r3q51", "source": "umass-crowdsource"}, "question": {"original": "Name something someone might do if they are mad about getting dumped.", "normalized": "name something someone might do if they are mad about getting dumped."}} 110 | {"metadata": {"id": "r3q52", "source": "umass-crowdsource"}, "question": {"original": "Name a reason someone might not want to invite their date to their office party.", "normalized": "name a reason someone might not want to invite their date to their office party."}} 111 | {"metadata": {"id": "r3q53", "source": "umass-crowdsource"}, "question": {"original": "Other than doing research, name something a professor probably does better than most people", "normalized": "other than doing research, name something a professor probably does better than most people"}} 112 | {"metadata": {"id": "r3q54", "source": "umass-crowdsource"}, "question": {"original": "Besides a trash can, name something people have in their front yard", "normalized": "besides a trash can, name something people have in their front yard"}} 113 | {"metadata": {"id": "r3q55", "source": "umass-crowdsource"}, "question": {"original": "Name something you might rent from a hiking store", "normalized": "name something you might rent from a hiking store"}} 114 | {"metadata": {"id": "r3q56", "source": "umass-crowdsource"}, "question": {"original": "Other than good service, name something a great restaurant has to have", "normalized": "other than good service, name something a great restaurant has to have"}} 115 | {"metadata": {"id": "r3q57", "source": "umass-crowdsource"}, "question": {"original": "Name something that you shine in order to look more professional", "normalized": "name something that you shine in order to look more professional"}} 116 | {"metadata": {"id": "r3q58", "source": "umass-crowdsource"}, "question": {"original": "Name a food that denture wearers should avoid.", "normalized": "name a food that denture wearers should avoid."}} 117 | {"metadata": {"id": "r3q59", "source": "umass-crowdsource"}, "question": {"original": "Name an annoying sound that might keep you up at night", "normalized": "name an annoying sound that might keep you up at night"}} 118 | {"metadata": {"id": "r3q60", "source": "umass-crowdsource"}, "question": {"original": "Name something you would probably learn how to do if you went to law school", "normalized": "name something you would probably learn how to do if you went to law school"}} 119 | {"metadata": {"id": "r3q61", "source": "umass-crowdsource"}, "question": {"original": "Name a vehicle that only holds up to two people.", "normalized": "name a vehicle that only holds up to two people."}} 120 | {"metadata": {"id": "r3q62", "source": "umass-crowdsource"}, "question": {"original": "Name something that can take the fun out of a baseball game.", "normalized": "name something that can take the fun out of a baseball game."}} 121 | {"metadata": {"id": "r3q63", "source": "umass-crowdsource"}, "question": {"original": "Name something kids can do but adults cannot.", "normalized": "name something kids can do but adults cannot."}} 122 | {"metadata": {"id": "r3q64", "source": "umass-crowdsource"}, "question": {"original": "Name something that some people are just naturally good at.", "normalized": "name something that some people are just naturally good at."}} 123 | {"metadata": {"id": "r3q65", "source": "umass-crowdsource"}, "question": {"original": "Name a way you can tell a house has not been abandonded.", "normalized": "name a way you can tell a house has not been abandonded."}} 124 | {"metadata": {"id": "r3q66", "source": "umass-crowdsource"}, "question": {"original": "Name a sign someone is unhappy with their birthday gift.", "normalized": "name a sign someone is unhappy with their birthday gift."}} 125 | {"metadata": {"id": "r3q67", "source": "umass-crowdsource"}, "question": {"original": "Name the first thing people do when they wake up in the morning", "normalized": "name the first thing people do when they wake up in the morning"}} 126 | {"metadata": {"id": "r3q68", "source": "umass-crowdsource"}, "question": {"original": "Name something that would make a bartender say they had a good day at work.", "normalized": "name something that would make a bartender say they had a good day at work."}} 127 | {"metadata": {"id": "r3q69", "source": "umass-crowdsource"}, "question": {"original": "Name a job that requires you to talk with children.", "normalized": "name a job that requires you to talk with children."}} 128 | {"metadata": {"id": "r3q70", "source": "umass-crowdsource"}, "question": {"original": "Name something you do for a friend who is sick.", "normalized": "name something you do for a friend who is sick."}} 129 | {"metadata": {"id": "r3q71", "source": "umass-crowdsource"}, "question": {"original": "Name a job that would be easy to do for blind people", "normalized": "name a job that would be easy to do for blind people"}} 130 | {"metadata": {"id": "r3q72", "source": "umass-crowdsource"}, "question": {"original": "Name something people have for breakfast that takes a long time to make", "normalized": "name something people have for breakfast that takes a long time to make"}} 131 | {"metadata": {"id": "r3q73", "source": "umass-crowdsource"}, "question": {"original": "Name something you might not buy when you go on a diet", "normalized": "name something you might not buy when you go on a diet"}} 132 | {"metadata": {"id": "r3q74", "source": "umass-crowdsource"}, "question": {"original": "Name something a kid might cry for", "normalized": "name something a kid might cry for"}} 133 | {"metadata": {"id": "r3q76", "source": "umass-crowdsource"}, "question": {"original": "Name a way that celebrities avoid the press", "normalized": "name a way that celebrities avoid the press"}} 134 | {"metadata": {"id": "r3q77", "source": "umass-crowdsource"}, "question": {"original": "Name an animal that doesn't make a recongizable sound", "normalized": "name an animal that doesn't make a recongizable sound"}} 135 | {"metadata": {"id": "r3q78", "source": "umass-crowdsource"}, "question": {"original": "Name something that people offer to a person who is pregnant.", "normalized": "name something that people offer to a person who is pregnant."}} 136 | {"metadata": {"id": "r3q79", "source": "umass-crowdsource"}, "question": {"original": "Other than ornaments, name something which might be placed on a christmas tree", "normalized": "other than ornaments, name something which might be placed on a christmas tree"}} 137 | {"metadata": {"id": "r3q80", "source": "umass-crowdsource"}, "question": {"original": "Name something fun that people can only do in winter.", "normalized": "name something fun that people can only do in winter."}} 138 | {"metadata": {"id": "r3q81", "source": "umass-crowdsource"}, "question": {"original": "Name something you have to unfold in order to use.", "normalized": "name something you have to unfold in order to use."}} 139 | {"metadata": {"id": "r3q83", "source": "umass-crowdsource"}, "question": {"original": "Name something people clean very often.", "normalized": "name something people clean very often."}} 140 | {"metadata": {"id": "r3q84", "source": "umass-crowdsource"}, "question": {"original": "Name a musical instrument that seems hard to learn to play.", "normalized": "name a musical instrument that seems hard to learn to play."}} 141 | {"metadata": {"id": "r3q85", "source": "umass-crowdsource"}, "question": {"original": "Name a type of stone you usually put in an engagement ring", "normalized": "name a type of stone you usually put in an engagement ring"}} 142 | {"metadata": {"id": "r3q86", "source": "umass-crowdsource"}, "question": {"original": "Besides a flag and name, name something each country has their own version of.", "normalized": "besides a flag and name, name something each country has their own version of."}} 143 | {"metadata": {"id": "r3q87", "source": "umass-crowdsource"}, "question": {"original": "Name something you would try to do if there was no gravity.", "normalized": "name something you would try to do if there was no gravity."}} 144 | {"metadata": {"id": "r3q88", "source": "umass-crowdsource"}, "question": {"original": "Name something a child might convince their parents to do.", "normalized": "name something a child might convince their parents to do."}} 145 | {"metadata": {"id": "r3q89", "source": "umass-crowdsource"}, "question": {"original": "Name a food you would not find in indian restaurant", "normalized": "name a food you would not find in indian restaurant"}} 146 | {"metadata": {"id": "r3q90", "source": "umass-crowdsource"}, "question": {"original": "Name a vegetable that grows underground?", "normalized": "name a vegetable that grows underground?"}} 147 | {"metadata": {"id": "r3q91", "source": "umass-crowdsource"}, "question": {"original": "Name a service that a dog can provide for a human in daily life.", "normalized": "name a service that a dog can provide for a human in daily life."}} 148 | {"metadata": {"id": "r3q92", "source": "umass-crowdsource"}, "question": {"original": "Name something embarrassing that might happen to someone while giving a presentation in a company meeting", "normalized": "name something embarrassing that might happen to someone while giving a presentation in a company meeting"}} 149 | {"metadata": {"id": "r3q93", "source": "umass-crowdsource"}, "question": {"original": "Name a fruit you might find in muffins", "normalized": "name a fruit you might find in muffins"}} 150 | {"metadata": {"id": "r3q94", "source": "umass-crowdsource"}, "question": {"original": "Name something about the people seated next to you which might make a flight unbearable", "normalized": "name something about the people seated next to you which might make a flight unbearable"}} 151 | {"metadata": {"id": "r3q95", "source": "umass-crowdsource"}, "question": {"original": "Name a place where kids are allowed to be loud", "normalized": "name a place where kids are allowed to be loud"}} 152 | {"metadata": {"id": "r3q98", "source": "umass-crowdsource"}, "question": {"original": "Name something that would make you end a blind date early", "normalized": "name something that would make you end a blind date early"}} 153 | {"metadata": {"id": "r3q99", "source": "umass-crowdsource"}, "question": {"original": "Name something that would impress you about a hotel if they give that for free.", "normalized": "name something that would impress you about a hotel if they give that for free."}} 154 | {"metadata": {"id": "r3q100", "source": "umass-crowdsource"}, "question": {"original": "Name a material that is often used in durable clothing.", "normalized": "name a material that is often used in durable clothing."}} 155 | -------------------------------------------------------------------------------- /data/dev/dev.predictions.gpt2finetuned.json: -------------------------------------------------------------------------------- 1 | {"r1q1": ["age", "name", "looks", "personality", "income", "many people"], "r1q2": ["sick", "emergency", "teacher", "test", "fight", "parent", "trouble", "", "crime", "problem", "bad teacher", "bully", "surprise", "child", "crisis", "date", "threat", "fighting", "bad behavior", "pick"], "r1q3": ["weapon", "sword", "car", "cell phone", "gun", "book", "computer", "knife", "boat", "hammer", "horse", "house", "staff", "mace", "cross", "pet", "pot", "bible", "monastic robe", "lance"], "r1q5": ["clean", "lock", "check mail", "shower", "wash dishes", "turn lights", "pack", "check kids", "take shower", "go bathroom", "set alarm", "get mail", "pick trash", "remove trash", "wipe", "leave keys", "locker", "wipe dishes", "laundry", "take pictures"], "r1q6": ["cake", "dessert", "", "pie", "recipe", "sandwich", "cream", "cupcake", "breakfast", "salad", "omelet", "chocolate", "meal", "cup", "chocolate cake", "snack", "new recipe", "oatmeal", "ice cream", "new house"], "r1q7": ["potato", "onion", "cabbage", "corn", "peppers", "pepper", "green beans", "bean", "beans", "vegetable", "peas", "watermelon", "spinach", "onions", "turnips", "mustard", "potatoes", "", "tomatoes", "cauliflower"], "r1q8": ["hotel", "car", "alcohol", "food", "eating", "travel", "cell phone", "driving", "bathroom", "airfare", "dinner", "sleeping", "smoking", "transportation", "drinking", "air travel", "drink", "sleep", "meals", "cars"], "r1q9": ["football", "wrestling", "tennis", "hockey", "boxing", "skiing", "racing", "baseball", "volleyball", "golf", "swimming", "gymnastics", "soccer"], "r1q10": ["garage", "home", "workshop", "office", "bedroom", "shop", "work", "store", "studio", "kitchen", "storage room", "storage", "repair shop", "living room", "bar", "museum", "house", "shed", "work shop", "car repair shop"], "r1q11": ["parents", "parent", "gun", "adults", "guns", "police", "family", "teachers", "safe", "security alarm", "security", "locks", "", "teacher", "laws", "good teachers", "safety", "age parents", "police officer", "armed guards"], "r1q12": ["house", "fire", "farm", "car", "park", "castle", "street", "pole", "circus", "earth", "church", "bar", "city", "building", "tower", "camp", "pole barn", "tree", "military base", "school"], "r1q14": ["hair spray", "something", "hairspray", "knot", "food", "insects", "water", "", "cat", "bug", "foreign object", "spider", "piece hair spray", "soap", "hairs", "piece food", "insect", "scent", "bits hair", "hair dryer"], "r1q16": ["desk", "computer", "telephones", "mouse", "fax machine", "typewriter", "printer", "pen", "telephone", "computers", "paper", "monitor", "office chair", "office desk", "printers", "keyboard", "telemarketer", "paper clips", "photocopier"], "r1q17": ["water", "food", "salt", "bottle water", "cheese", "ice cream", "oil", "alcohol", "drink", "sports drink", "ice", "meat", "fish", "butter", "milk", "chocolate", "beer", "cookie", "bottle", "towel"], "r1q18": ["shirt", "coat", "pants", "underwear", "belt", "shoes", "suit", "clothes", "hat", "jeans", "jacket", "underpants", "shorts", "clothing", "boots", "vest", "gloves", "dress", "belts", "undergarments"], "r1q19": ["charity", "military", "animal charity", "cause charity", "cause", "organization", "relief", "animal shelter", "ALS", "cause sick", "Red Cross", "animal hospital", "arts", "sick", "American Cancer Society", "children's hospital", "relief effort", "cancer research", "animal welfare", "child care"], "r1q20": ["coupons", "food", "products", "gift", "free food", "candy", "flyers", "merchandise", "tickets", "cookies", "gifts", "discounts", "free gift", "drink", "beer", "t-shirts", "shirts", "coupon", "souvenir", "free coffee"], "r2q3": ["pizza", "lasagna", "cheese salad", "cheese", "cheese steak", "cheese pizza", "cheese soup", "macaroni cheese", "cheese plate", "cheese sauce", "cheese sandwich", "casserole", "cheese toast", "macaroni & cheese", "cheese stew", "french fries", "cheesy", "", "ravioli", "cheese cake"], "r2q4": ["cold", "work", "protect", "swimming", "fire", "working", "flu", "sunburn", "fight", "doctor's office", "hiking", "hot", "skiing", "they're allergic", "prevent infection", "emergency", "", "rain", "infection", "sick"], "r2q5": ["smile", "kiss", "talk", "laugh", "love", "share room", "they're married", "share house", "friendly", "sharing room", "like", "they're good friends", "share bathroom", "money", "married", "walk together", "fight", "kissing", "sharing bathroom", "they're together"], "r2q6": ["dishes", "toilet", "kitchen", "furniture", "windows", "bathroom", "lights", "door", "floor", "plumbing", "appliances", "floors", "appliance", "television", "stove", "bulbs", "roof", "towels", "washing machine", "fridge"], "r2q7": ["drink", "fight", "smoke", "steal", "lie", "drink alcohol", "break curfew", "drugs", "cause trouble", "kill", "get tattoo", "drive", "talk", "eat", "litter", "pick nose", "use alcohol", "hurt", "use cell phone", "get job"], "r2q8": ["police officer", "doctor", "firefighter", "security guard", "reporter", "bus driver", "police", "night guard", "driver", "nurse", "guard", "policeman", "night", "cop", "nanny", "construction", "teacher", "mail carrier", "journalist", "worker"], "r2q9": ["they're slow", "they're friendly", "slow", "they're rude", "teach", "they're strict", "rude", "they're fast", "they're lazy", "show", "they're aggressive", "they're loud", "strict", "know", "they're easy", "they're busy", "they're demanding", "loud", "they're nice", "they're much"], "r2q10": ["job", "money", "friends", "much money", "affair", "jobs", "many toys", "parents", "bad grades", "attitude", "car", "much energy", "opinion", "wrong clothes", "sex", "clothes", "personality", "ex", "manners", "kids"], "r2q11": ["kiss", "talk", "drink", "hold hands", "share drink", "share food", "share meals", "share drinks", "laugh", "party", "share bathroom", "date", "flirt", "share bed", "share meal", "cook", "shop", "exchange gifts", "share rooms", "show affection"], "r2q12": ["furniture", "pool", "lawn", "garden", "appliances", "kitchen", "house", "tools", "roof", "bathtub", "bed", "bathroom", "decorations", "plumbing", "carpet", "food", "new roof", "new kitchen", "toilet", "car"], "r2q14": ["go college", "travel", "work", "move", "get married", "move away", "go dates", "go date", "stay home", "join military", "go", "party", "go work", "enter military", "try job", "shop", "find job", "enroll college", "start career", "become police officer"], "r2q15": ["name", "names", "people", "faces", "person", "face", "addresses", "family photos", "family"], "r2q18": ["earthquakes", "death", "love", "fire", "divorce", "birth", "tragedy", "wars", "marriage", "plane crash", "deaths", "war", "weather", "birth child", "disasters", "car accident", "crime", "disaster", "death child", "baby"], "r2q19": ["rope", "people", "tree", "ladder", "person", "ball", "fence", "cat", "bird", "something", "chain", "jump", "spider", "man", "", "gun", "shark", "flag", "bar", "dog"], "r2q20": ["products", "milk", "candy", "paper", "items", "food", "cereal", "toys", "bags", "variety", "fruit", "sugar", "shelf", "snacks", "magazines", "clothes", "chips", "snack", "water", "books"], "r2q21": ["cheese", "sauce", "base", "pizza", "pepperoni", "lot cheese", "aioli", "flour", "peppers", "pizza sauce", "toppings", "dough", "meat", "pie", "oven", "tomatoes", "hot dog", "pie pan", "bread", "mozzarella"], "r2q23": ["win", "\"score", "", "\"go", "\"point", "score", "go", "\"nothing", "\"drive", "game", "\"strike", "\"yell", "\"tough\"", "\"touchdown", "\"fire\"", "\"cheer", "\"go\"", "\"good", "\"good game\"", "touchdowns"], "r2q25": ["friendly", "smaller", "cute", "easier house", "affectionate", "better", "fluffy", "they're friendly", "gentle", "easier control", "safer", "", "furry", "cat's personality", "cleaner", "they're smaller", "quieter", "size", "much smaller", "they're less aggressive"], "r2q26": ["dog", "cat", "snake", "fox", "lion", "frog", "horse", "bear", "pig", "elephant", "fish", "sheep", "dogs", "monkey", "kangaroo", "cats", "dolphin", "bull", "penguins", "bunny"], "r2q27": ["smile", "brush", "swallow", "talk", "bite nails", "breath", "speak", "hold breath", "floss", "answer phone", "", "complain", "ask questions", "mouthwash", "squeeze", "swallow gum", "bite", "drink coffee", "laugh", "fill mouth"], "r2q30": ["sick", "emergency", "traffic", "stuck", "hurry", "tired", "stuck traffic", "gas", "waiting", "traffic jam", "phone", "use bathroom", "stranded", "night", "get gas", "injured", "lost", "", "rain", "motorcycle"], "r2q31": ["mice", "cat", "snake", "rats", "fish", "cats", "dog", "mouse"], "r2q32": ["afraid", "shy", "sick", "scared", "", "they're afraid", "they're shy", "they're sick", "like", "age", "know", "they're scared", "jealous", "teased", "smart", "can't speak", "young", "often sick", "lot trouble", "temper"], "r2q35": ["military", "president", "police officer", "journalist", "police", "politician", "business", "lawyer", "media", "billionaire", "security guard", "actor", "judge", "private security", "religious leader", "businessman", "doctor", "private sector", "private military", "state"], "r2q37": ["conversation", "fight", "argument", "something", "bad breath", "phone call", "bad habit", "sick", "someone else", "noise", "cold", "bad conversation", "nervous", "situation", "pregnant", "busy", "job", "feeling sick", "something bad", "drunk"], "r2q38": ["cars", "clothes", "car", "house", "food", "furniture", "things", "appliances", "television", "books", "pets", "products", "wine", "watches", "appliance", "family photos", "household", "jewelry", "houses", "time"], "r2q39": ["fighting", "riding bike", "martial arts", "sports", "drinking", "fight", "swimming", "skiing", "dancing", "gambling", "climbing", "fishing", "racing", "jogging", "running", "wrestling", "horseback riding", "driving", "traveling", "action"], "r2q40": ["dark", "death", "scary", "germs", "heights", "older people", "people", "ghost", "snakes", "scary people", "blood", "scary movie", "age", "alone", "aging", "shadows", "things", "tigers", "scary movies", "getting older"], "r2q42": ["bad weather", "weather", "lot", "little", "", "flight", "day early", "argument", "day", "illness", "week", "delayed", "late", "hours", "flight delay", "couple", "flight attendant", "sick", "month", "bit"], "r2q43": ["dogs", "dog", "animals", "fence", "trees", "birds", "ants", "trash", "sign", "people", "tree", "snake", "bird droppings", "insects", "signs", "barking dog", "mice", "rats", "cats", "worms"], "r2q44": ["house", "teeth", "body", "clothes", "feet", "home", "head", "family", "eyes", "mind", "wallet", "car", "mouth", "ears", "hands", "stomach", "toilet", "legs", "nose", "purse"], "r2q45": ["illness", "stress", "job", "stressful job", "age", "heart attack", "bad diet", "cold", "bad habit", "lot stress", "sickness", "condition", "family member", "weight loss", "health problems", "diet", "weight", "smoking", "argument", "health problem"], "r2q46": ["good service", "they're friendly", "friendly", "service", "they're nice", "nice", "bad service", "great service", "he/she nice", "they're good service", "they're rude", "thanksgiving", ": good service", "he's friendly", "he's nice", "they're good server", "tip", "well done", "rude", "good"], "r2q47": ["glass", "glasses", "mirror", "teeth", "windows", "eggs", "things", "shoes", "window", "food", "something", "lightbulb", "rules", "dishes", "hair", "chain", "nails", "tire", "light bulbs", "locks"], "r2q49": ["bar", "restaurant", "office", "hotel", "airport", "store", "movie theater", "work", "bank", "mall", "", "movie theatre", "movie", "public transit", "public restroom"]} -------------------------------------------------------------------------------- /data/dev/dev.predictions.human.jsonl: -------------------------------------------------------------------------------- 1 | {"r1q1": ["age", "something", "its roots", "if you tell the truth", "birthdate", "your likes", "name", "his birthday", "profession", "truth", "his way of thinking", "their favorite food", "his favorite song", "what they like", "their likes", "sentiments", "favorite food", "lie", "day of birth", "birthday", "favorite color", "love", "angry", "feelings", "years"]} 2 | {"r1q2": ["fight", "misbehavior", "bullying", "sick", "a fight", "fights", "underperformance", "kids fight", "skfd2e", "did some mischief", "parents reunion", "fail an exam", "bad grades", "they fight", "notes", "lack", "he got in a fight", "bad behavior", "scolding", "their kids"]} 3 | {"r1q3": ["gun", "wife", "knife", "pornography", "hell", "guns", "a car", "luxuries", "sex toys", "alcohol", "pants", "red clothes", "two", "cry", "adult magazines", "car", "a large car", "wives", "hair", "jean"]} 4 | {"r1q5": ["dress", "eat", "close the door", "breakfast", "have breakfast", "to comb", "drink water", "bath", "pray", "drink", "get dressed", "food"]} 5 | {"r1q6": ["cake", "market", "ice cream", "flour", "umbrella", "pastel", "flan"]} 6 | {"r1q7": ["pumpkin", "watermelon", "lettuce", "pineapple", "auyama", "aswdc", "cabbage", "broccoli", "tomato", "the pumpkin"]} 7 | {"r1q8": ["jewelry", "suitcases", "car", "boats", "mercedes", "concierge", "their time", "vehicle", "chains", "be at home", "perfume", "cardigan", "bed", "house", "own car", "laundry", "computer", "his own bed", "rock stars", "clothes", "the family", "the house", "private bathroom", "comfort", "shirt", "using diamonds"]} 8 | {"r1q9": ["football", "soccer", "hockey", "baseball", "american football", "golf", "sky", "rugby", "racing", "lot"]} 9 | {"r1q10": ["room", "gym", "car", "workshop", "game room", "office", "video game room", "store", "warehouse", "pub", "garage store", "temporary housing", "dress", "house", "games", "laboratory", "february", "brewery room", "work office", "deposit"]} 10 | {"r1q11": ["belt", "house", "parents", "toys", "butter", "mom", "seatbelt", "walker", "school", "mon", "be with the parents", "cribs", "the competent authorities", "watch tv on house", "cameras", "their parents", "beeb car", "family", "sun protector", "police", "water", "safe", "that", "car belt", "blanket", "helmet", "a blanket"]} 11 | {"r1q12": ["street", "north pole", "south pole", "an avenue", "park", "streets", "hotel", "bakery", "alameda", "a field of football", "avenue", "the street", "court", "pole", "umbrella", "strippers bar", "city", "farol", "red", "highway", "fire station", "the corners"]} 12 | {"r1q14": ["gum", "hair comb", "bubble gum", "comb", "lice", "powder", "hook hair", "sand", "leaf", "tail", "too long", "weadaaw", "red", "dirt", "dandruff", "bugs", "sugar"]} 13 | {"r1q16": ["printer", "stapler", "folders", "computer", "air conditioning", "fax", "file cabinet", "carpets", "shredder", "umbrella", "scanner", "office table", "paper", "leaves", "photocopier", "luggage", "work table"]} 14 | {"r1q17": ["cake", "shoe", "shoes", "candy", "beer", "grease", "coke", "apple", "food", "donuts", "pizza", "sodas", "protein", "not", "alcoholic beverages", "sneakers", "water", "chocolate", "something", "alcohol"]} 15 | {"r1q18": ["underwear", "panties", "boxer", "shirt", "blouse", "dress", "sweater", "shoes", "boxer shorts", "brassier", "lingerie", "ueyr", "socks", "north dakota"]} 16 | {"r1q19": ["cancer", "hiv", "water", "family", "blue", "a pandemic", "affected children", "church", "to help people", "covid-19", "blood", "love", "aids", "orphans", "toy", "blood donation", "sick or homeless children", "diabetes", "famine", "alcoholics anonymous", "cancer associations", "kids with cancer", "sickness", "courage", "you"]} 17 | {"r1q20": ["candy", "samples", "free sample", "sweet", "coupons", "coupon", "cookies", "clothes", "food", "promotions", "cheese", "brochures", "review", "strict", "sandwiches", "laptops", "fragrance", "prices", "bags", "coffee", "advertising", "almanacs", "food samples"]} 18 | {"r2q3": ["pizza", "lasagna", "cheesecake", "macaroni", "mac and cheese", "cheese", "hamburger", "cheeseburger", "banana with cheese", "red", "quesadilla", "macaroni and cheese", "made"]} 19 | {"r2q4": ["cold", "protection", "virus", "protect", "covid19", "take care of your hands", "coronavirus", "winter", "safety", "avoid the cold", "cut plant with thorns", "dress", "security", "by the cold", "covid-19", "pennant shape", "cleaning"]} 20 | {"r2q5": ["trust", "love", "hugs", "they laugh together a lot", "share", "confidence", "jokes", "nice, sincerity", "ahmed", "they hug", "friendship", "greeting", "laugh", "they spend it together", "wolfgang", "bbf", "be together", "smiles", "red", "people", "sweetie", "hug", "laughs", "kiss"]} 21 | {"r2q6": ["light bulbs", "toilet paper", "furniture", "food", "mats", "none", "paint", "the pipe", "trash", "pencil", "water filter", "tablecloth", "fence", "bulbs", "curtains", "mailbox", "toothbrush", "light bulb", "chair", "painting", "garbage", "wkldjewf", "tap", "replaced", "spotlights", "coleto"]} 22 | {"r2q7": ["run", "steal", "fight", "cry", "disobey", "parents", "cousin", "to fight at school", "consume drugs", "do not run", "tell lies", "dvw", "drink alcohol", "watch out", "don't lie", "sleep late", "to eat", "drink alcoholic beverages", "antics", "cross the street", "tell bad words", "curse"]} 23 | {"r2q8": ["vigilant", "surveillance", "night guard", "watch man", "barack obama", "appenn", "driver", "work home", "security", "guard", "watch", "mita", "bar", "police", "production", "yellow", "doctor", "call center", "to pee", "bartender", "restaurant", "programming", "nurse"]} 24 | {"r2q9": ["none", "pain", "instructors", "damaged machines", "too demanding", "abuse", "muscles", "very loud", "disinterested", "let", "demanding", "they don't train well", "screams", "to touch them", "eating disorders", "they are sexy", "he does not like weak people", "too strict", "yell", "sexual abuse", "sweaty", "pressure", "nest", "those are many exercises", "they send a lot", "trying to hit on them", "strict"]} 25 | {"r2q10": ["drugs", "time", "bad behavior", "bad friends", "videogame", "breeding", "expenses", "red", "disorder", "abortion", "lie", "drug", "a piercing", "gun", "the mess", "food", "naughty", "tattoo", "character", "dirty clothes", "none", "bad habits", "ffee"]} 26 | {"r2q11": ["sleep", "play", "sleep together", "eat", "to tell secrets", "sweet", "partying", "go to beer", "share in their houses", "poop", "talk", "watch movies", "tell them secrets", "go to the cinema", "eat together", "dance", "speak", "hug", "twelve", "hugs", "kiss", "jwhfi", "two", "kisses", "trust", "play, share, read", "spring", "laugh", "go for a walk"]} 27 | {"r2q12": ["swimming pool", "dog", "dog house", "pet", "piano", "pool", "nba", "chair", "garden", "backyard", "pruner", "more space", "roof", "block", "dress", "mower", "bathtub", "money", "garden decorations", "plants for your garden", "pets"]} 28 | {"r2q14": ["work", "to work", "a gap year", "house", "book", "tree", "party", "courses", "go to work", "study", "travel", "webjfheu", "start a business", "running", "college", "take course"]} 29 | {"r2q15": ["family", "photos", "wedding", "birthday", "eat", "wjdw", "party", "love", "names", "often", "childhood", "birthdate", "first love", "first kiss", "memories", "shower", "name", "two", "history", "girlfriend", "anecdotes"]} 30 | {"r2q18": ["corruption", "poverty", "news", "falls", "famine", "drug trafficking", "sunrise", "animal abuse", "eating", "the truth", "wetting", "embarrassing", "burns", "sex", "pollution", "political mismanagement", "magic", "spontaneity", "misleading news", "kill", "cleaning", "treason", "people fears", "shopping", "win the lottery", "lottery"]} 31 | {"r2q19": ["kangaroo", "bunny", "frog", "rabbit", "ball", "rana", "car", "barack obama", "animal", "cricket", "rope", "dog", "a kid", "cerca", "february", "trampoline"]} 32 | {"r2q20": ["milk", "cookies", "often", "butter", "corn flakes", "oat bars", "leaflets", "umbrella", "cookie", "eleven"]} 33 | {"r2q21": ["cheese", "flour", "tomato", "sauce", "tomatoes", "fluor", "mass", "pizza dough", "drought", "wheat flour", "they send a lot", "bugger", "baking"]} 34 | {"r2q23": ["run", "stop", "move", "defending", "come on", "we can", "come on!", "mita", "game", "come on, run fast", "foul", "time", "monday", "outside", "intensity", "barack obama", "good luck"]} 35 | {"r2q25": ["are not afraid of water", "spring", "won't bark", "cats are independent", "fidelity", "little", "cats are calmer", "because he hunts mice", "cute", "they are best friends", "they are more quiet", "yellow", "less food", "qrygqf", "no bark", "the cat is smaller", "depression", "cats are cleaner", "they are more passive", "charisma", "does not make noise", "the cat hunts mice", "responsibility", "silence", "they are quiet", "live in apartment", "cats make less noise", "blue", "size", "they are not so big"]} 36 | {"r2q26": ["dog", "their", "umbrella", "ape", "monkey", "wizard", "parrot"]} 37 | {"r2q27": ["think", "nervous", "wait", "read a magazine", "talk", "carie", "bite", "check the phone", "look at the ceiling", "open their mouth", "cry", "reading magazines", "stay relaxed", "eyes closed", "spring", "open mouth", "close eyes", "close their eyes", "whdeufg", "teeth", "be calm", "phone", "spit", "look everywhere", "look", "read", "red"]} 38 | {"r2q30": ["accident", "flat tire", "pissing", "scratched", "sdjcfehkjfe", "for go to the bathroom", "two", "reason", "to pee", "puncture", "animal", "mechanical failure", "dizziness", "pooing", "broken tire", "fault", "cops", "fatigue", "wetting", "speckled rubber", "call", "to urinate", "accidents", "lack of gasoline", "sleep", "a trunk", "dream"]} 39 | {"r2q31": ["hamster", "dogs", "lion", "lizard", "turtle", "chicken", "tiger", "hamsters", "monkey", "ferret", "parrot", "mouse", "snake", "rabbit", "mono", "the hamsters"]} 40 | {"r2q32": ["bullying", "toys", "aggressive", "because he doesn't lend him his toys", "envy", "fear", "jealousy", "competition", "attitude", "because he was upset", "pain", "bad odor", "annoying", "because it is bad", "precaution", "because he doesn't lend him the toys", "fight", "different ages", "love", "bully", "shyness"]} 41 | {"r2q35": ["president", "influencers", "ceo", "police", "singer", "doctor", "musician", "politics", "lawyer", "which", "attorney", "microsoft", "minister", "banking and finances", "entrepreneur", "secretary", "medical", "nasa", "engineering", "wood", "judge", "fiscal"]} 42 | {"r2q37": ["treason", "lies", "lie", "fight", "sad", "liars", "their attitude", "cheated", "nothing", "pain", "cheating", "a lie", "death", "sadness", "stupidity", "the gossip", "to speak ill of me", "betrayal", "something", "angry", "a discussion"]} 43 | {"r2q38": ["food", "bed", "phone", "house", "washing machine", "clothes", "mustard sauce", "mobile", "mattresses", "water", "oven", "gas", "mattress", "wine", "market", "phones", "canned", "furniture", "coffee", "ornaments", "fridge"]} 44 | {"r2q39": ["fights", "fight", "action", "umbrella", "play golf", "spies", "fly", "to revive", "dance", "private detective", "jump in vehicles", "kiss", "cruises", "jumanji", "jump from building", "risk their lives", "love", "street racing", "mercenary", "robberies", "a lot of action", "fiction", "jump from skyscraper", "travel", "jump off a bridge", "nothing", "to play"]} 45 | {"r2q40": ["darkness", "dark", "clowns", "coco", "insects", "terror movies", "death", "spider", "being alone", "the coconut", "wardrobe", "ghost", "halloween", "die", "chucky", "ghosts", "boogeyman", "stories"]} 46 | {"r2q42": ["storm", "death of a family member", "death of a relative", "hurricane", "disaster", "love", "business meeting", "passport", "ticket", "medical emergency", "fear", "coronavirus", "lost trip", "seat", "dead", "a virus", "commissions", "unforeseen meeting", "storms", "weather", "accident", "bad weather", "delay", "the family", "a pandemic", "work commitment"]} 47 | {"r2q43": ["dog", "garden", "head", "messenger", "a big dog", "brave dog", "house", "food", "a dog", "a gun", "problems", "traffic", "an angry dog", "bike", "elephant", "red", "angry dog", "doorbell", "feerar"]} 48 | {"r2q44": ["house", "money", "car", "pets", "nose", "watch", "toy", "coin", "red", "clothes", "fridge", "hungry", "smaller", "tattoos", "shoe", "marbles", "happiness", "a house", "their car", "heart", "table", "stomach"]} 49 | {"r2q45": ["exercise", "diet", "training", "exercises", "depression", "gym", "jogging", "to run", "run", "illness", "house", "sickness", "running", "water", "fruits", "disease"]} 50 | {"r2q46": ["good service", "good attention", "service", "attention", "excellent service", "amiability", "barack obama", "good", "health", "bad service", "friends", "services provided", "breakfast", "cute", "nice"]} 51 | {"r2q47": ["glass", "paper", "cup", "plate", "egg", "mirror", "a box", "cookie fortune", "sdvf", "ice", "sheet", "bed", "crystal", "phone", "mobile", "a pen", "glasses", "anime"]} 52 | {"r2q49": ["park", "coffee shop", "restaurant", "psychiatrist", "office", "bank", "hospital", "rest room", "place", "doctor's office", "restaurant at beach", "forest", "conference room", "receptionist", "supermarket", "work", "doctors", "meeting room", "psychology", "marketing company", "central park", "pub"]} 53 | -------------------------------------------------------------------------------- /data/omitted/omitted.jsonl: -------------------------------------------------------------------------------- 1 | {"metadata": {"id": "omission.q121", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name Something Little Boys Love To Build Models Of. ", "normalized": "name something little boys love to build models of."}, "answers": {"raw": {"cars": 47, "airplanes": 30, "legos": 10, "trucks": 5, "trains": 3, "buildings": 2}, "clusters": {"omission.q121.0": {"count": 47, "answers": ["cars"]}, "omission.q121.1": {"count": 30, "answers": ["airplanes"]}, "omission.q121.2": {"count": 10, "answers": ["legos"]}, "omission.q121.3": {"count": 5, "answers": ["trucks"]}, "omission.q121.4": {"count": 3, "answers": ["trains"]}, "omission.q121.5": {"count": 2, "answers": ["buildings"]}}}, "num": {"answers": 97, "clusters": 6}} 2 | {"metadata": {"id": "omission.q390", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name Something That Little Girls Do When They Get Together ", "normalized": "name something that little girls do when they get together"}, "answers": {"raw": {"giggle": 33, "play dolls": 27, "dress up/makeover": 16, "play house": 11, "tea party": 6, "jump rope": 4}, "clusters": {"omission.q390.0": {"count": 33, "answers": ["giggle"]}, "omission.q390.1": {"count": 27, "answers": ["play dolls"]}, "omission.q390.2": {"count": 16, "answers": ["dress up/makeover"]}, "omission.q390.3": {"count": 11, "answers": ["play house"]}, "omission.q390.4": {"count": 6, "answers": ["tea party"]}, "omission.q390.5": {"count": 4, "answers": ["jump rope"]}}}, "num": {"answers": 97, "clusters": 6}} 3 | {"metadata": {"id": "omission.q488", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name something a teenage girl might envy about other teenage girls. ", "normalized": "name something a teenage girl might envy about other teenage girls."}, "answers": {"raw": {"figure": 26, "hair": 23, "clothes": 18}, "clusters": {"omission.q488.0": {"count": 26, "answers": ["figure"]}, "omission.q488.1": {"count": 23, "answers": ["hair"]}, "omission.q488.2": {"count": 18, "answers": ["clothes"]}}}, "num": {"answers": 67, "clusters": 3}} 4 | {"metadata": {"id": "omission.q642", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name something little girls pretend to be: ", "normalized": "name something little girls pretend to be:"}, "answers": {"raw": {"mommies": 51, "princesses": 13, "nurses": 11, "teachers": 8, "brides": 7, "actresses": 4, "ballerinas": 3}, "clusters": {"omission.q642.0": {"count": 51, "answers": ["mommies"]}, "omission.q642.1": {"count": 13, "answers": ["princesses"]}, "omission.q642.2": {"count": 11, "answers": ["nurses"]}, "omission.q642.3": {"count": 8, "answers": ["teachers"]}, "omission.q642.4": {"count": 7, "answers": ["brides"]}, "omission.q642.5": {"count": 4, "answers": ["actresses"]}, "omission.q642.6": {"count": 3, "answers": ["ballerinas"]}}}, "num": {"answers": 97, "clusters": 7}} 5 | {"metadata": {"id": "omission.q708", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name something even little girls plan about their wedding. ", "normalized": "name something even little girls plan about their wedding."}, "answers": {"raw": {"gown": 71, "location": 4, "flowers": 4, "honeymoon": 4, "cake": 3}, "clusters": {"omission.q708.0": {"count": 71, "answers": ["gown"]}, "omission.q708.1": {"count": 4, "answers": ["location"]}, "omission.q708.2": {"count": 4, "answers": ["flowers"]}, "omission.q708.3": {"count": 4, "answers": ["honeymoon"]}, "omission.q708.4": {"count": 3, "answers": ["cake"]}}}, "num": {"answers": 86, "clusters": 5}} 6 | {"metadata": {"id": "omission.q1753", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name A Present Most Boys Would Want For The Holidays ", "normalized": "name a present most boys would want for the holidays"}, "answers": {"raw": {"bike": 29, "videogames": 25, "toy car": 14, "ipod": 11, "gi joe": 9, "football": 5}, "clusters": {"omission.q1753.0": {"count": 29, "answers": ["bike"]}, "omission.q1753.1": {"count": 25, "answers": ["videogames"]}, "omission.q1753.2": {"count": 14, "answers": ["toy car"]}, "omission.q1753.3": {"count": 11, "answers": ["ipod"]}, "omission.q1753.4": {"count": 9, "answers": ["gi joe"]}, "omission.q1753.5": {"count": 5, "answers": ["football"]}}}, "num": {"answers": 93, "clusters": 6}} 7 | {"metadata": {"id": "omission.q2515", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name something women want to do \"before they're too old to do it\". ", "normalized": "name something women want to do \"before they're too old to do it\"."}, "answers": {"raw": {"baby": 50, "travel": 22, "skydive": 5, "marry": 4, "university": 2}, "clusters": {"omission.q2515.0": {"count": 50, "answers": ["baby"]}, "omission.q2515.1": {"count": 22, "answers": ["travel"]}, "omission.q2515.2": {"count": 5, "answers": ["skydive"]}, "omission.q2515.3": {"count": 4, "answers": ["marry"]}, "omission.q2515.4": {"count": 2, "answers": ["university"]}}}, "num": {"answers": 83, "clusters": 5}} 8 | {"metadata": {"id": "omission.q2631", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Tell Me Something About A Boy\u2019s Appearance That Might Make his Date\u2019s Disapprove Of Him ", "normalized": "tell me something about a boy\u2019s appearance that might make his date\u2019s disapprove of him"}, "answers": {"raw": {"long hair": 28, "tattoos": 27, "inappropriate dress": 20, "piercings": 17, "dirty/unkempt": 3, "facial hair": 3}, "clusters": {"omission.q2631.0": {"count": 28, "answers": ["long hair"]}, "omission.q2631.1": {"count": 27, "answers": ["tattoos"]}, "omission.q2631.2": {"count": 20, "answers": ["inappropriate dress"]}, "omission.q2631.3": {"count": 17, "answers": ["piercings"]}, "omission.q2631.4": {"count": 3, "answers": ["dirty/unkempt"]}, "omission.q2631.5": {"count": 3, "answers": ["facial hair"]}}}, "num": {"answers": 98, "clusters": 6}} 9 | {"metadata": {"id": "omission.q2815", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "What do you call someone that scares easily. ", "normalized": "what do you call someone that scares easily."}, "answers": {"raw": {"fraidy cat": 47, "chicken": 26, "wimp": 17, "sissy": 10}, "clusters": {"omission.q2815.0": {"count": 47, "answers": ["fraidy cat"]}, "omission.q2815.1": {"count": 26, "answers": ["chicken"]}, "omission.q2815.2": {"count": 17, "answers": ["wimp"]}, "omission.q2815.3": {"count": 10, "answers": ["sissy"]}}}, "num": {"answers": 100, "clusters": 4}} 10 | {"metadata": {"id": "omission.q3011", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name Something Little Boys Can\u2019t Wait To Grow Up And Do. ", "normalized": "name something little boys can\u2019t wait to grow up and do."}, "answers": {"raw": {"drive": 49, "play sports": 15, "be like daddy": 12, "shave": 11, "date": 8, "be a firefighter": 5}, "clusters": {"omission.q3011.0": {"count": 49, "answers": ["drive"]}, "omission.q3011.1": {"count": 15, "answers": ["play sports"]}, "omission.q3011.2": {"count": 12, "answers": ["be like daddy"]}, "omission.q3011.3": {"count": 11, "answers": ["shave"]}, "omission.q3011.4": {"count": 8, "answers": ["date"]}, "omission.q3011.5": {"count": 5, "answers": ["be a firefighter"]}}}, "num": {"answers": 100, "clusters": 6}} 11 | {"metadata": {"id": "omission.q3369", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name A Present Most Girls Would Want For The Holidays. ", "normalized": "name a present most girls would want for the holidays."}, "answers": {"raw": {"jewelry": 36, "doll": 30}, "clusters": {"omission.q3369.0": {"count": 36, "answers": ["jewelry"]}, "omission.q3369.1": {"count": 30, "answers": ["doll"]}}}, "num": {"answers": 66, "clusters": 2}} 12 | {"metadata": {"id": "omission.q3889", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name a question single women hate to be asked. ", "normalized": "name a question single women hate to be asked."}, "answers": {"raw": {"about marriage": 42, "how old are you?": 35, "are you dating?": 7, "about weight": 7, "zodiac sign?": 3, "are you gay?": 2}, "clusters": {"omission.q3889.0": {"count": 42, "answers": ["about marriage"]}, "omission.q3889.1": {"count": 35, "answers": ["how old are you?"]}, "omission.q3889.2": {"count": 7, "answers": ["are you dating?"]}, "omission.q3889.3": {"count": 7, "answers": ["about weight"]}, "omission.q3889.4": {"count": 3, "answers": ["zodiac sign?"]}, "omission.q3889.5": {"count": 2, "answers": ["are you gay?"]}}}, "num": {"answers": 96, "clusters": 6}} 13 | {"metadata": {"id": "omission.q4808", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name a game little boys play that they don't want girls to join in. ", "normalized": "name a game little boys play that they don't want girls to join in."}, "answers": {"raw": {"football": 28, "baseball": 15, "cops & robbers": 11, "marbles": 7, "video games": 7, "cowboys & indians": 6}, "clusters": {"omission.q4808.0": {"count": 28, "answers": ["football"]}, "omission.q4808.1": {"count": 15, "answers": ["baseball"]}, "omission.q4808.2": {"count": 11, "answers": ["cops & robbers"]}, "omission.q4808.3": {"count": 7, "answers": ["marbles"]}, "omission.q4808.4": {"count": 7, "answers": ["video games"]}, "omission.q4808.5": {"count": 6, "answers": ["cowboys & indians"]}}}, "num": {"answers": 74, "clusters": 6}} 14 | {"metadata": {"id": "omission.q5195", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name something little boys don't like. ", "normalized": "name something little boys don't like."}, "answers": {"raw": {"girls": 54, "baths": 12, "vegetables": 8, "dolls": 5, "kisses": 4}, "clusters": {"omission.q5195.0": {"count": 54, "answers": ["girls"]}, "omission.q5195.1": {"count": 12, "answers": ["baths"]}, "omission.q5195.2": {"count": 8, "answers": ["vegetables"]}, "omission.q5195.3": {"count": 5, "answers": ["dolls"]}, "omission.q5195.4": {"count": 4, "answers": ["kisses"]}}}, "num": {"answers": 83, "clusters": 5}} 15 | {"metadata": {"id": "omission.q5426", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Tell Me A Girl\u2019s Name That Begins With \u201cS.\u201d ", "normalized": "tell me a girl\u2019s name that begins with \u201cs.\u201d"}, "answers": {"raw": {"sarah": 35, "sue/susan/suzanne": 17, "samantha": 17, "stephanie": 15, "sally": 7, "sandy": 5}, "clusters": {"omission.q5426.0": {"count": 35, "answers": ["sarah"]}, "omission.q5426.1": {"count": 17, "answers": ["sue/susan/suzanne"]}, "omission.q5426.2": {"count": 17, "answers": ["samantha"]}, "omission.q5426.3": {"count": 15, "answers": ["stephanie"]}, "omission.q5426.4": {"count": 7, "answers": ["sally"]}, "omission.q5426.5": {"count": 5, "answers": ["sandy"]}}}, "num": {"answers": 96, "clusters": 6}} 16 | {"metadata": {"id": "omission.q5884", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name The Age Girls Stop Playing With Dolls. (Numeric Only) ", "normalized": "name the age girls stop playing with dolls. (numeric only)"}, "answers": {"raw": {"12": 36, "13": 19, "10": 16, "9": 8, "11": 8, "8": 6, "14": 5}, "clusters": {"omission.q5884.0": {"count": 36, "answers": ["12"]}, "omission.q5884.1": {"count": 19, "answers": ["13"]}, "omission.q5884.2": {"count": 16, "answers": ["10"]}, "omission.q5884.3": {"count": 8, "answers": ["9"]}, "omission.q5884.4": {"count": 8, "answers": ["11"]}, "omission.q5884.5": {"count": 6, "answers": ["8"]}, "omission.q5884.6": {"count": 5, "answers": ["14"]}}}, "num": {"answers": 98, "clusters": 7}} 17 | {"metadata": {"id": "omission.q6145", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name a woman known for having nice legs. ", "normalized": "name a woman known for having nice legs."}, "answers": {"raw": {"heidi klum": 8, "julia roberts": 10, "angelina jolie": 13, "marilyn monroe": 24, "cindy crawford": 5}, "clusters": {"omission.q6145.0": {"count": 8, "answers": ["heidi klum"]}, "omission.q6145.1": {"count": 10, "answers": ["julia roberts"]}, "omission.q6145.2": {"count": 13, "answers": ["angelina jolie"]}, "omission.q6145.3": {"count": 24, "answers": ["marilyn monroe"]}, "omission.q6145.4": {"count": 5, "answers": ["cindy crawford"]}}}, "num": {"answers": 60, "clusters": 5}} 18 | {"metadata": {"id": "omission.q6157", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name Something A Man Would Wear If He Were To Impersonate A Woman ", "normalized": "name something a man would wear if he were to impersonate a woman"}, "answers": {"raw": {"dress": 30, "wig": 26, "high heels": 12}, "clusters": {"omission.q6157.0": {"count": 30, "answers": ["dress"]}, "omission.q6157.1": {"count": 26, "answers": ["wig"]}, "omission.q6157.2": {"count": 12, "answers": ["high heels"]}}}, "num": {"answers": 68, "clusters": 3}} 19 | {"metadata": {"id": "omission.q6162", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name A Reason Why A Woman Wouldn\u2019t Want Her Picture Taken At The Water Park. ", "normalized": "name a reason why a woman wouldn\u2019t want her picture taken at the water park."}, "answers": {"raw": {"swimsuit": 0, "fat": 39}, "clusters": {"omission.q6162.0": {"count": 0, "answers": ["swimsuit"]}, "omission.q6162.1": {"count": 39, "answers": ["fat"]}}}, "num": {"answers": 39, "clusters": 2}} 20 | {"metadata": {"id": "omission.q6805", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name an electrical appliance most women want on a desert island. ", "normalized": "name an electrical appliance most women want on a desert island."}, "answers": {"raw": {"blow dryer": 19, "blower": 19, "hair dryer": 19, "dryer": 19, "refrigerator": 18, "icebox": 18, "fridge": 18, "freezer": 18, "tube": 16, "tv": 16, "television": 16, "on television": 16, "boob tube": 16, "microwave": 12, "stove": 9, "boiler": 9, "furnace": 9, "range": 9, "oven": 9, "ac": 5, "air conditioner": 5}, "clusters": {"omission.q6805.0": {"count": 19, "answers": ["blow dryer"]}, "omission.q6805.1": {"count": 19, "answers": ["blower"]}, "omission.q6805.2": {"count": 19, "answers": ["hair dryer"]}, "omission.q6805.3": {"count": 19, "answers": ["dryer"]}, "omission.q6805.4": {"count": 18, "answers": ["refrigerator"]}, "omission.q6805.5": {"count": 18, "answers": ["icebox"]}, "omission.q6805.6": {"count": 18, "answers": ["fridge"]}, "omission.q6805.7": {"count": 18, "answers": ["freezer"]}, "omission.q6805.8": {"count": 16, "answers": ["tube"]}, "omission.q6805.9": {"count": 16, "answers": ["tv"]}, "omission.q6805.10": {"count": 16, "answers": ["television"]}, "omission.q6805.11": {"count": 16, "answers": ["on television"]}, "omission.q6805.12": {"count": 16, "answers": ["boob tube"]}, "omission.q6805.13": {"count": 12, "answers": ["microwave"]}, "omission.q6805.14": {"count": 9, "answers": ["stove"]}, "omission.q6805.15": {"count": 9, "answers": ["boiler"]}, "omission.q6805.16": {"count": 9, "answers": ["furnace"]}, "omission.q6805.17": {"count": 9, "answers": ["range"]}, "omission.q6805.18": {"count": 9, "answers": ["oven"]}, "omission.q6805.19": {"count": 5, "answers": ["ac"]}, "omission.q6805.20": {"count": 5, "answers": ["air conditioner"]}}}, "num": {"answers": 295, "clusters": 21}} 21 | {"metadata": {"id": "omission.q6867", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Tell me an age when girls start thinking about boys.(Numeric only) ", "normalized": "tell me an age when girls start thinking about boys.(numeric only)"}, "answers": {"raw": {"12": 27, "13": 26, "10": 12, "14": 11, "11": 7, "6": 5, "5": 5}, "clusters": {"omission.q6867.0": {"count": 27, "answers": ["12"]}, "omission.q6867.1": {"count": 26, "answers": ["13"]}, "omission.q6867.2": {"count": 12, "answers": ["10"]}, "omission.q6867.3": {"count": 11, "answers": ["14"]}, "omission.q6867.4": {"count": 7, "answers": ["11"]}, "omission.q6867.5": {"count": 5, "answers": ["6"]}, "omission.q6867.6": {"count": 5, "answers": ["5"]}}}, "num": {"answers": 93, "clusters": 7}} 22 | {"metadata": {"id": "omission.q6997", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "When it comes to appearance, name something women only do because men want them to. ", "normalized": "when it comes to appearance, name something women only do because men want them to."}, "answers": {"raw": {"wear makeup": 24, "sexy lingerie": 20, "wear tight pants": 12, "style hair": 10, "wear high heels": 9, "shave/wax": 8, "get \"boob job\"": 7}, "clusters": {"omission.q6997.0": {"count": 24, "answers": ["wear makeup"]}, "omission.q6997.1": {"count": 20, "answers": ["sexy lingerie"]}, "omission.q6997.2": {"count": 12, "answers": ["wear tight pants"]}, "omission.q6997.3": {"count": 10, "answers": ["style hair"]}, "omission.q6997.4": {"count": 9, "answers": ["wear high heels"]}, "omission.q6997.5": {"count": 8, "answers": ["shave/wax"]}, "omission.q6997.6": {"count": 7, "answers": ["get \"boob job\""]}}}, "num": {"answers": 90, "clusters": 7}} 23 | {"metadata": {"id": "omission.q7458", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name The Age That A Boy First Becomes Interested In Girls. ", "normalized": "name the age that a boy first becomes interested in girls."}, "answers": {"raw": {"13": 37, "12": 33, "10": 15, "14": 11}, "clusters": {"omission.q7458.0": {"count": 37, "answers": ["13"]}, "omission.q7458.1": {"count": 33, "answers": ["12"]}, "omission.q7458.2": {"count": 15, "answers": ["10"]}, "omission.q7458.3": {"count": 11, "answers": ["14"]}}}, "num": {"answers": 96, "clusters": 4}} 24 | {"metadata": {"id": "omission.q7592", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name an animal little boys use to frighten girls. ", "normalized": "name an animal little boys use to frighten girls."}, "answers": {"raw": {"snake": 25, "spider": 24}, "clusters": {"omission.q7592.0": {"count": 25, "answers": ["snake"]}, "omission.q7592.1": {"count": 24, "answers": ["spider"]}}}, "num": {"answers": 49, "clusters": 2}} 25 | {"metadata": {"id": "omission.q7848", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name something that looks better on young girls than older women: ", "normalized": "name something that looks better on young girls than older women:"}, "answers": {"raw": {"miniskirt": 63, "bathing suit": 19, "ponytail": 5, "ribbon": 3, "shorts": 3, "makeup": 2}, "clusters": {"omission.q7848.0": {"count": 63, "answers": ["miniskirt"]}, "omission.q7848.1": {"count": 19, "answers": ["bathing suit"]}, "omission.q7848.2": {"count": 5, "answers": ["ponytail"]}, "omission.q7848.3": {"count": 3, "answers": ["ribbon"]}, "omission.q7848.4": {"count": 3, "answers": ["shorts"]}, "omission.q7848.5": {"count": 2, "answers": ["makeup"]}}}, "num": {"answers": 95, "clusters": 6}} 26 | {"metadata": {"id": "omission.q8066", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name something that boys hate doing because they think only sissies do it.` ", "normalized": "name something that boys hate doing because they think only sissies do it.`"}, "answers": {"raw": {"housework": 25, "dance": 16, "play with dolls": 10, "cry": 9, "kiss girls": 8, "bathe": 6}, "clusters": {"omission.q8066.0": {"count": 25, "answers": ["housework"]}, "omission.q8066.1": {"count": 16, "answers": ["dance"]}, "omission.q8066.2": {"count": 10, "answers": ["play with dolls"]}, "omission.q8066.3": {"count": 9, "answers": ["cry"]}, "omission.q8066.4": {"count": 8, "answers": ["kiss girls"]}, "omission.q8066.5": {"count": 6, "answers": ["bathe"]}}}, "num": {"answers": 74, "clusters": 6}} 27 | {"metadata": {"id": "omission.q9464", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "Name something about himself that a man might avoid telling a date. ", "normalized": "name something about himself that a man might avoid telling a date."}, "answers": {"raw": {"married/involved": 32, "no job/money": 16, "his age": 16, "he has kids": 8, "past relat'nships": 7, "has an illness": 3, "he's gay": 2}, "clusters": {"omission.q9464.0": {"count": 32, "answers": ["married/involved"]}, "omission.q9464.1": {"count": 16, "answers": ["no job/money"]}, "omission.q9464.2": {"count": 16, "answers": ["his age"]}, "omission.q9464.3": {"count": 8, "answers": ["he has kids"]}, "omission.q9464.4": {"count": 7, "answers": ["past relat'nships"]}, "omission.q9464.5": {"count": 3, "answers": ["has an illness"]}, "omission.q9464.6": {"count": 2, "answers": ["he's gay"]}}}, "num": {"answers": 84, "clusters": 7}} 28 | {"metadata": {"id": "omission.q9750", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "They say the wife is always the last to know. Name something that she might be the last to know about her husband. ", "normalized": "they say the wife is always the last to know. name something that she might be the last to know about her husband."}, "answers": {"raw": {"cheating/affair": 77, "finances/bills": 9, "he's gay/bi": 6, "lost his job": 4, "gambling problem": 2}, "clusters": {"omission.q9750.0": {"count": 77, "answers": ["cheating/affair"]}, "omission.q9750.1": {"count": 9, "answers": ["finances/bills"]}, "omission.q9750.2": {"count": 6, "answers": ["he's gay/bi"]}, "omission.q9750.3": {"count": 4, "answers": ["lost his job"]}, "omission.q9750.4": {"count": 2, "answers": ["gambling problem"]}}}, "num": {"answers": 98, "clusters": 5}} 29 | {"metadata": {"id": "omission.q9907", "source": "https://www.familyfeudinfo.com"}, "question": {"original": "We surveyed 100 women...Name something women do for their little boys that they also do for their husbands. ", "normalized": "we surveyed 100 women...name something women do for their little boys that they also do for their husbands."}, "answers": {"raw": {"cook": 26, "clean up after": 16, "laundry": 15, "kiss/hug": 10, "shop for them": 7, "dress them": 7}, "clusters": {"omission.q9907.0": {"count": 26, "answers": ["cook"]}, "omission.q9907.1": {"count": 16, "answers": ["clean up after"]}, "omission.q9907.2": {"count": 15, "answers": ["laundry"]}, "omission.q9907.3": {"count": 10, "answers": ["kiss/hug"]}, "omission.q9907.4": {"count": 7, "answers": ["shop for them"]}, "omission.q9907.5": {"count": 7, "answers": ["dress them"]}}}, "num": {"answers": 81, "clusters": 6}} 30 | -------------------------------------------------------------------------------- /data/test/test.questions.jsonl: -------------------------------------------------------------------------------- 1 | {"metadata": {"id": "r1q4", "source": "umass-crowdsource"}, "question": {"original": "Name a complaint people have about their parents.", "normalized": "name a complaint people have about their parents."}} 2 | {"metadata": {"id": "r1q13", "source": "umass-crowdsource"}, "question": {"original": "Name a hobby better suited for city living than country living.", "normalized": "name a hobby better suited for city living than country living."}} 3 | {"metadata": {"id": "r1q15", "source": "umass-crowdsource"}, "question": {"original": "Name a sport that takes a long time to play.", "normalized": "name a sport that takes a long time to play."}} 4 | {"metadata": {"id": "r2q2", "source": "umass-crowdsource"}, "question": {"original": "Name something babies probably cry about.", "normalized": "name something babies probably cry about."}} 5 | {"metadata": {"id": "r2q16", "source": "umass-crowdsource"}, "question": {"original": "Name a characteristic commonly associated with professors.", "normalized": "name a characteristic commonly associated with professors."}} 6 | {"metadata": {"id": "r2q22", "source": "umass-crowdsource"}, "question": {"original": "Name something a small-town politician would do while campaigning.", "normalized": "name something a small-town politician would do while campaigning."}} 7 | {"metadata": {"id": "r2q29", "source": "umass-crowdsource"}, "question": {"original": "Name something parents are proud of their children for.", "normalized": "name something parents are proud of their children for."}} 8 | {"metadata": {"id": "r2q33", "source": "umass-crowdsource"}, "question": {"original": "Name something you would need if you were lost in Antarctica.", "normalized": "name something you would need if you were lost in antarctica."}} 9 | {"metadata": {"id": "r2q36", "source": "umass-crowdsource"}, "question": {"original": "Name something annoying a person might do at fast food restaurant when there's a long line behind them.", "normalized": "name something annoying a person might do at fast food restaurant when there's a long line behind them."}} 10 | {"metadata": {"id": "r2q41", "source": "umass-crowdsource"}, "question": {"original": "Name something a boss might do and then tell their employees not to do.", "normalized": "name something a boss might do and then tell their employees not to do."}} 11 | {"metadata": {"id": "r2q48", "source": "umass-crowdsource"}, "question": {"original": "Name something you would find in someone's car which is not part of the car itself.", "normalized": "name something you would find in someone's car which is not part of the car itself."}} 12 | {"metadata": {"id": "r2q50", "source": "umass-crowdsource"}, "question": {"original": "Name something you might forget at a hotel room.", "normalized": "name something you might forget at a hotel room."}} 13 | {"metadata": {"id": "r3q1", "source": "umass-crowdsource"}, "question": {"original": "Name a reason someone might not want to stay in the hotel they booked", "normalized": "name a reason someone might not want to stay in the hotel they booked"}} 14 | {"metadata": {"id": "r3q3", "source": "umass-crowdsource"}, "question": {"original": "Name something that a person usually does after they get home after running outside in the sun?", "normalized": "name something that a person usually does after they get home after running outside in the sun?"}} 15 | {"metadata": {"id": "r3q4", "source": "umass-crowdsource"}, "question": {"original": "Name a reason why a restaurant might be very empty", "normalized": "name a reason why a restaurant might be very empty"}} 16 | {"metadata": {"id": "r3q6", "source": "umass-crowdsource"}, "question": {"original": "Name a dish that is very messy to eat", "normalized": "name a dish that is very messy to eat"}} 17 | {"metadata": {"id": "r3q7", "source": "umass-crowdsource"}, "question": {"original": "Name something on which kids might need their parents signature", "normalized": "name something on which kids might need their parents signature"}} 18 | {"metadata": {"id": "r3q8", "source": "umass-crowdsource"}, "question": {"original": "Name a body part that might hurt when a person wears a high heeled shoe?", "normalized": "name a body part that might hurt when a person wears a high heeled shoe?"}} 19 | {"metadata": {"id": "r3q9", "source": "umass-crowdsource"}, "question": {"original": "Apart from their coach, name someone who plays an important role in an athletes life?", "normalized": "apart from their coach, name someone who plays an important role in an athletes life?"}} 20 | {"metadata": {"id": "r3q11", "source": "umass-crowdsource"}, "question": {"original": "Name something you do while eating dinner at home that you can't do in a restaurant.", "normalized": "name something you do while eating dinner at home that you can't do in a restaurant."}} 21 | {"metadata": {"id": "r3q12", "source": "umass-crowdsource"}, "question": {"original": "Name something people do to wake themselves up if they are tired.", "normalized": "name something people do to wake themselves up if they are tired."}} 22 | {"metadata": {"id": "r3q13", "source": "umass-crowdsource"}, "question": {"original": "Name something many people are happy to do alone.", "normalized": "name something many people are happy to do alone."}} 23 | {"metadata": {"id": "r3q14", "source": "umass-crowdsource"}, "question": {"original": "Name a job where your clothes get really wet.", "normalized": "name a job where your clothes get really wet."}} 24 | {"metadata": {"id": "r3q15", "source": "umass-crowdsource"}, "question": {"original": "Name a reason why people may not return clothes they bought which don't fit them.", "normalized": "name a reason why people may not return clothes they bought which don't fit them."}} 25 | {"metadata": {"id": "r3q16", "source": "umass-crowdsource"}, "question": {"original": "Name a mode of transportation that is easy to use while caring for children", "normalized": "name a mode of transportation that is easy to use while caring for children"}} 26 | {"metadata": {"id": "r3q17", "source": "umass-crowdsource"}, "question": {"original": "Name something their parents do which children brag about.", "normalized": "name something their parents do which children brag about."}} 27 | {"metadata": {"id": "r3q19", "source": "umass-crowdsource"}, "question": {"original": "Name something that when you forget to carry might prevent you from entering a bar", "normalized": "name something that when you forget to carry might prevent you from entering a bar"}} 28 | {"metadata": {"id": "r3q20", "source": "umass-crowdsource"}, "question": {"original": "Name a reason a person would be eager to change careers", "normalized": "name a reason a person would be eager to change careers"}} 29 | {"metadata": {"id": "r3q21", "source": "umass-crowdsource"}, "question": {"original": "Name something you might need if you own a car", "normalized": "name something you might need if you own a car"}} 30 | {"metadata": {"id": "r3q22", "source": "umass-crowdsource"}, "question": {"original": "Name something a policecar has which a regular car does not", "normalized": "name something a policecar has which a regular car does not"}} 31 | {"metadata": {"id": "r3q23", "source": "umass-crowdsource"}, "question": {"original": "Name a food you could still eat if you had a queasy stomach", "normalized": "name a food you could still eat if you had a queasy stomach"}} 32 | {"metadata": {"id": "r3q24", "source": "umass-crowdsource"}, "question": {"original": "Name a serious situation where you might prepare a speech", "normalized": "name a serious situation where you might prepare a speech"}} 33 | {"metadata": {"id": "r3q25", "source": "umass-crowdsource"}, "question": {"original": "Name an activity a driver might engage in which could cause an accident", "normalized": "name an activity a driver might engage in which could cause an accident"}} 34 | {"metadata": {"id": "r3q26", "source": "umass-crowdsource"}, "question": {"original": "Name something you wouldn't touch without washing your hands first.", "normalized": "name something you wouldn't touch without washing your hands first."}} 35 | {"metadata": {"id": "r3q27", "source": "umass-crowdsource"}, "question": {"original": "Name something people do on airplanes if they are scared.", "normalized": "name something people do on airplanes if they are scared."}} 36 | {"metadata": {"id": "r3q28", "source": "umass-crowdsource"}, "question": {"original": "Name an activity where it would be dangerous to wear headphones.", "normalized": "name an activity where it would be dangerous to wear headphones."}} 37 | {"metadata": {"id": "r3q29", "source": "umass-crowdsource"}, "question": {"original": "Name something that a detective might look for at a burglary.", "normalized": "name something that a detective might look for at a burglary."}} 38 | {"metadata": {"id": "r3q30", "source": "umass-crowdsource"}, "question": {"original": "Name something that would make a driver honk their horn.", "normalized": "name something that would make a driver honk their horn."}} 39 | {"metadata": {"id": "r3q32", "source": "umass-crowdsource"}, "question": {"original": "Other than being stopped by a cop, name a reason why someone might have to pull off to the side of the road while driving.", "normalized": "other than being stopped by a cop, name a reason why someone might have to pull off to the side of the road while driving."}} 40 | {"metadata": {"id": "r3q33", "source": "umass-crowdsource"}, "question": {"original": "Besides buying one, name a way someone might be able to get a house.", "normalized": "besides buying one, name a way someone might be able to get a house."}} 41 | {"metadata": {"id": "r3q34", "source": "umass-crowdsource"}, "question": {"original": "Name a reason for people to go into graduate school", "normalized": "name a reason for people to go into graduate school"}} 42 | {"metadata": {"id": "r3q35", "source": "umass-crowdsource"}, "question": {"original": "Name a food which usually has low-calorie", "normalized": "name a food which usually has low-calorie"}} 43 | {"metadata": {"id": "r3q36", "source": "umass-crowdsource"}, "question": {"original": "Name a reason people prefer to live in big cities rather than small towns.", "normalized": "name a reason people prefer to live in big cities rather than small towns."}} 44 | {"metadata": {"id": "r3q37", "source": "umass-crowdsource"}, "question": {"original": "Name an accessory that might be given to you if you go join a cooking class?", "normalized": "name an accessory that might be given to you if you go join a cooking class?"}} 45 | {"metadata": {"id": "r3q38", "source": "umass-crowdsource"}, "question": {"original": "Name a feeling that you might experience after having a heavy meal in the afternoon", "normalized": "name a feeling that you might experience after having a heavy meal in the afternoon"}} 46 | {"metadata": {"id": "r3q39", "source": "umass-crowdsource"}, "question": {"original": "Name a place that you can make new friends as an adult.", "normalized": "name a place that you can make new friends as an adult."}} 47 | {"metadata": {"id": "r3q40", "source": "umass-crowdsource"}, "question": {"original": "Name something you'd be embarassed to have in the car if you got pulled over.", "normalized": "name something you'd be embarassed to have in the car if you got pulled over."}} 48 | {"metadata": {"id": "r3q41", "source": "umass-crowdsource"}, "question": {"original": "Name a place you might have to wait in line.", "normalized": "name a place you might have to wait in line."}} 49 | {"metadata": {"id": "r3q42", "source": "umass-crowdsource"}, "question": {"original": "Name something you might buy to show your support for a sports team", "normalized": "name something you might buy to show your support for a sports team"}} 50 | {"metadata": {"id": "r3q43", "source": "umass-crowdsource"}, "question": {"original": "Name an occupation in which you'd be at greater risk of getting burned", "normalized": "name an occupation in which you'd be at greater risk of getting burned"}} 51 | {"metadata": {"id": "r3q45", "source": "umass-crowdsource"}, "question": {"original": "Name something a queen has but most woman dont have", "normalized": "name something a queen has but most woman dont have"}} 52 | {"metadata": {"id": "r3q46", "source": "umass-crowdsource"}, "question": {"original": "Name an occupation where you might need a car", "normalized": "name an occupation where you might need a car"}} 53 | {"metadata": {"id": "r3q47", "source": "umass-crowdsource"}, "question": {"original": "If your pizza was delivered very late what would be a possible reason for that.", "normalized": "if your pizza was delivered very late what would be a possible reason for that."}} 54 | {"metadata": {"id": "r3q48", "source": "umass-crowdsource"}, "question": {"original": "Name something people should not do when they are angry", "normalized": "name something people should not do when they are angry"}} 55 | {"metadata": {"id": "r3q49", "source": "umass-crowdsource"}, "question": {"original": "Name something people do ahead of time when family is coming to stay", "normalized": "name something people do ahead of time when family is coming to stay"}} 56 | {"metadata": {"id": "r3q50", "source": "umass-crowdsource"}, "question": {"original": "Name an event where someone might meet a lot of new people.", "normalized": "name an event where someone might meet a lot of new people."}} 57 | {"metadata": {"id": "r3q51", "source": "umass-crowdsource"}, "question": {"original": "Name something someone might do if they are mad about getting dumped.", "normalized": "name something someone might do if they are mad about getting dumped."}} 58 | {"metadata": {"id": "r3q52", "source": "umass-crowdsource"}, "question": {"original": "Name a reason someone might not want to invite their date to their office party.", "normalized": "name a reason someone might not want to invite their date to their office party."}} 59 | {"metadata": {"id": "r3q53", "source": "umass-crowdsource"}, "question": {"original": "Other than doing research, name something a professor probably does better than most people", "normalized": "other than doing research, name something a professor probably does better than most people"}} 60 | {"metadata": {"id": "r3q54", "source": "umass-crowdsource"}, "question": {"original": "Besides a trash can, name something people have in their front yard", "normalized": "besides a trash can, name something people have in their front yard"}} 61 | {"metadata": {"id": "r3q55", "source": "umass-crowdsource"}, "question": {"original": "Name something you might rent from a hiking store", "normalized": "name something you might rent from a hiking store"}} 62 | {"metadata": {"id": "r3q56", "source": "umass-crowdsource"}, "question": {"original": "Other than good service, name something a great restaurant has to have", "normalized": "other than good service, name something a great restaurant has to have"}} 63 | {"metadata": {"id": "r3q57", "source": "umass-crowdsource"}, "question": {"original": "Name something that you shine in order to look more professional", "normalized": "name something that you shine in order to look more professional"}} 64 | {"metadata": {"id": "r3q58", "source": "umass-crowdsource"}, "question": {"original": "Name a food that denture wearers should avoid.", "normalized": "name a food that denture wearers should avoid."}} 65 | {"metadata": {"id": "r3q59", "source": "umass-crowdsource"}, "question": {"original": "Name an annoying sound that might keep you up at night", "normalized": "name an annoying sound that might keep you up at night"}} 66 | {"metadata": {"id": "r3q60", "source": "umass-crowdsource"}, "question": {"original": "Name something you would probably learn how to do if you went to law school", "normalized": "name something you would probably learn how to do if you went to law school"}} 67 | {"metadata": {"id": "r3q61", "source": "umass-crowdsource"}, "question": {"original": "Name a vehicle that only holds up to two people.", "normalized": "name a vehicle that only holds up to two people."}} 68 | {"metadata": {"id": "r3q62", "source": "umass-crowdsource"}, "question": {"original": "Name something that can take the fun out of a baseball game.", "normalized": "name something that can take the fun out of a baseball game."}} 69 | {"metadata": {"id": "r3q63", "source": "umass-crowdsource"}, "question": {"original": "Name something kids can do but adults cannot.", "normalized": "name something kids can do but adults cannot."}} 70 | {"metadata": {"id": "r3q64", "source": "umass-crowdsource"}, "question": {"original": "Name something that some people are just naturally good at.", "normalized": "name something that some people are just naturally good at."}} 71 | {"metadata": {"id": "r3q65", "source": "umass-crowdsource"}, "question": {"original": "Name a way you can tell a house has not been abandonded.", "normalized": "name a way you can tell a house has not been abandonded."}} 72 | {"metadata": {"id": "r3q66", "source": "umass-crowdsource"}, "question": {"original": "Name a sign someone is unhappy with their birthday gift.", "normalized": "name a sign someone is unhappy with their birthday gift."}} 73 | {"metadata": {"id": "r3q67", "source": "umass-crowdsource"}, "question": {"original": "Name the first thing people do when they wake up in the morning", "normalized": "name the first thing people do when they wake up in the morning"}} 74 | {"metadata": {"id": "r3q68", "source": "umass-crowdsource"}, "question": {"original": "Name something that would make a bartender say they had a good day at work.", "normalized": "name something that would make a bartender say they had a good day at work."}} 75 | {"metadata": {"id": "r3q69", "source": "umass-crowdsource"}, "question": {"original": "Name a job that requires you to talk with children.", "normalized": "name a job that requires you to talk with children."}} 76 | {"metadata": {"id": "r3q70", "source": "umass-crowdsource"}, "question": {"original": "Name something you do for a friend who is sick.", "normalized": "name something you do for a friend who is sick."}} 77 | {"metadata": {"id": "r3q71", "source": "umass-crowdsource"}, "question": {"original": "Name a job that would be easy to do for blind people", "normalized": "name a job that would be easy to do for blind people"}} 78 | {"metadata": {"id": "r3q72", "source": "umass-crowdsource"}, "question": {"original": "Name something people have for breakfast that takes a long time to make", "normalized": "name something people have for breakfast that takes a long time to make"}} 79 | {"metadata": {"id": "r3q73", "source": "umass-crowdsource"}, "question": {"original": "Name something you might not buy when you go on a diet", "normalized": "name something you might not buy when you go on a diet"}} 80 | {"metadata": {"id": "r3q74", "source": "umass-crowdsource"}, "question": {"original": "Name something a kid might cry for", "normalized": "name something a kid might cry for"}} 81 | {"metadata": {"id": "r3q76", "source": "umass-crowdsource"}, "question": {"original": "Name a way that celebrities avoid the press", "normalized": "name a way that celebrities avoid the press"}} 82 | {"metadata": {"id": "r3q77", "source": "umass-crowdsource"}, "question": {"original": "Name an animal that doesn't make a recongizable sound", "normalized": "name an animal that doesn't make a recongizable sound"}} 83 | {"metadata": {"id": "r3q78", "source": "umass-crowdsource"}, "question": {"original": "Name something that people offer to a person who is pregnant.", "normalized": "name something that people offer to a person who is pregnant."}} 84 | {"metadata": {"id": "r3q79", "source": "umass-crowdsource"}, "question": {"original": "Other than ornaments, name something which might be placed on a christmas tree", "normalized": "other than ornaments, name something which might be placed on a christmas tree"}} 85 | {"metadata": {"id": "r3q80", "source": "umass-crowdsource"}, "question": {"original": "Name something fun that people can only do in winter.", "normalized": "name something fun that people can only do in winter."}} 86 | {"metadata": {"id": "r3q81", "source": "umass-crowdsource"}, "question": {"original": "Name something you have to unfold in order to use.", "normalized": "name something you have to unfold in order to use."}} 87 | {"metadata": {"id": "r3q83", "source": "umass-crowdsource"}, "question": {"original": "Name something people clean very often.", "normalized": "name something people clean very often."}} 88 | {"metadata": {"id": "r3q84", "source": "umass-crowdsource"}, "question": {"original": "Name a musical instrument that seems hard to learn to play.", "normalized": "name a musical instrument that seems hard to learn to play."}} 89 | {"metadata": {"id": "r3q85", "source": "umass-crowdsource"}, "question": {"original": "Name a type of stone you usually put in an engagement ring", "normalized": "name a type of stone you usually put in an engagement ring"}} 90 | {"metadata": {"id": "r3q86", "source": "umass-crowdsource"}, "question": {"original": "Besides a flag and name, name something each country has their own version of.", "normalized": "besides a flag and name, name something each country has their own version of."}} 91 | {"metadata": {"id": "r3q87", "source": "umass-crowdsource"}, "question": {"original": "Name something you would try to do if there was no gravity.", "normalized": "name something you would try to do if there was no gravity."}} 92 | {"metadata": {"id": "r3q88", "source": "umass-crowdsource"}, "question": {"original": "Name something a child might convince their parents to do.", "normalized": "name something a child might convince their parents to do."}} 93 | {"metadata": {"id": "r3q89", "source": "umass-crowdsource"}, "question": {"original": "Name a food you would not find in indian restaurant", "normalized": "name a food you would not find in indian restaurant"}} 94 | {"metadata": {"id": "r3q90", "source": "umass-crowdsource"}, "question": {"original": "Name a vegetable that grows underground?", "normalized": "name a vegetable that grows underground?"}} 95 | {"metadata": {"id": "r3q91", "source": "umass-crowdsource"}, "question": {"original": "Name a service that a dog can provide for a human in daily life.", "normalized": "name a service that a dog can provide for a human in daily life."}} 96 | {"metadata": {"id": "r3q92", "source": "umass-crowdsource"}, "question": {"original": "Name something embarrassing that might happen to someone while giving a presentation in a company meeting", "normalized": "name something embarrassing that might happen to someone while giving a presentation in a company meeting"}} 97 | {"metadata": {"id": "r3q93", "source": "umass-crowdsource"}, "question": {"original": "Name a fruit you might find in muffins", "normalized": "name a fruit you might find in muffins"}} 98 | {"metadata": {"id": "r3q94", "source": "umass-crowdsource"}, "question": {"original": "Name something about the people seated next to you which might make a flight unbearable", "normalized": "name something about the people seated next to you which might make a flight unbearable"}} 99 | {"metadata": {"id": "r3q95", "source": "umass-crowdsource"}, "question": {"original": "Name a place where kids are allowed to be loud", "normalized": "name a place where kids are allowed to be loud"}} 100 | {"metadata": {"id": "r3q98", "source": "umass-crowdsource"}, "question": {"original": "Name something that would make you end a blind date early", "normalized": "name something that would make you end a blind date early"}} 101 | {"metadata": {"id": "r3q99", "source": "umass-crowdsource"}, "question": {"original": "Name something that would impress you about a hotel if they give that for free.", "normalized": "name something that would impress you about a hotel if they give that for free."}} 102 | {"metadata": {"id": "r3q100", "source": "umass-crowdsource"}, "question": {"original": "Name a material that is often used in durable clothing.", "normalized": "name a material that is often used in durable clothing."}} 103 | --------------------------------------------------------------------------------