├── input.txt ├── README.md ├── bert_token_embed.py ├── .gitignore └── LICENSE /input.txt: -------------------------------------------------------------------------------- 1 | Hello World ! 2 | I'm hankcs 3 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # BERT token level embedding 2 | 3 | This tiny script demonstrates how to generate BERT token level embeddings. As BERT use word piece as tokenizer, OOV will be segmented into several word pieces. This script has implemented `2` strategies to handle that case. 4 | 5 | In the following chapters, we'll show how to generate BERT embeddings for each token without pain. 6 | 7 | ## 1. Install BERT server and download pre-trained BERT model 8 | 9 | Run following command: 10 | 11 | ```bash 12 | pip3 install bert-serving-server # server 13 | pip3 install bert-serving-client # client, independent of `bert-serving-server` 14 | wget https://storage.googleapis.com/bert_models/2018_10_18/uncased_L-12_H-768_A-12.zip 15 | unzip uncased_L-12_H-768_A-12.zip 16 | cd uncased_L-12_H-768_A-12/ 17 | bert-serving-start -model_dir . -pooling_strategy NONE -show_tokens_to_client -max_seq_len 256 18 | ``` 19 | 20 | ## 2. Generate embeddings 21 | 22 | Put the text you want to embed into `input.txt` : 23 | 24 | ``` 25 | Hello World ! 26 | I'm hankcs 27 | ``` 28 | 29 | Run `bert_token_embed.py`, you will get a pickle file called `output.pkl`. It stores a list of `numpy.ndarray` 30 | 31 | ``` 32 | : [array([[-0.10005677, 0.10111555, 0.3707362 , ..., -0.79261583, 33 | -0.29630244, -0.43822828], 34 | [-0.1717627 , -0.08768683, 0.57421064, ..., -0.43223655, 35 | -0.02188881, -0.2638072 ], 36 | [-1.2841692 , -1.4125137 , -0.92776453, ..., 0.26873824, 37 | -0.03885475, 0.14489302]], dtype=float32), array([[-0.28254002, -0.01273985, -0.2916504 , ..., -0.99867177, 38 | 0.7456796 , 0.3703635 ], 39 | [-0.8595818 , -0.09063847, -0.14206652, ..., -0.10226044, 40 | 0.4216262 , -0.20428266]], dtype=float32)] 41 | ``` 42 | 43 | The i-th `ndarray` is the BERT embedding of i-th sentence, of size n x c, where n is the sentence length, c is the dimension of BERT embedding(usually `768` or `1024`). For example, `Hello World !` is embedded as `3x768` tensor, since it contains `3` tokens. 44 | 45 | As you may notice, `I'm hankcs` is embedded as `2x768` tensor. My ID `hankcs` is a typical OOV, which is segmented to `2` word pieces. 46 | 47 | ``` 48 | 'hank', '##cs' 49 | ``` 50 | 51 | Each word piece has its own vector. There are `2` strategies implemented as `2` functions to merge them into one: 52 | 53 | 1. `embed_last_token`: Use the last word piece as the representation of whole token. 54 | 2. `embed_sum`: Use the average vector instead. 55 | 56 | ## Licence 57 | 58 | #### Apache License 2.0 59 | 60 | -------------------------------------------------------------------------------- /bert_token_embed.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | # Author: hankcs 3 | # Date: 2019-01-13 15:01 4 | import pickle 5 | 6 | import numpy as np 7 | from bert_serving.client import BertClient 8 | 9 | bc = BertClient(ip='127.0.0.1') # ip address of the server 10 | 11 | 12 | def embed_last_token(text): 13 | result = bc.encode(text, show_tokens=True) 14 | # print(result) 15 | batch = [] 16 | for sent, tensor, tokens in zip(text, result[0], result[1]): 17 | valid = [] 18 | tid = 0 19 | buffer = '' 20 | words = sent.lower().split() 21 | for i, t in enumerate(tokens): 22 | if t == '[CLS]' or t == '[SEP]': 23 | continue 24 | else: 25 | if t.startswith('##'): 26 | t = t[2:] 27 | buffer += t 28 | if buffer == words[tid]: 29 | valid.append(i) 30 | buffer = '' 31 | tid += 1 32 | # print(len(valid)) 33 | # exit() 34 | if len(valid) != len(sent.split()) or tid != len(words): 35 | print(valid) 36 | print(sent.split()) 37 | print(result[1]) 38 | batch.append(tensor[valid, :]) 39 | return batch 40 | 41 | 42 | def embed_sum(text): 43 | result = bc.encode(text, show_tokens=True) 44 | # print(result) 45 | batch = [] 46 | for sent, tensor, tokens in zip(text, result[0], result[1]): 47 | token_tensor = [] 48 | sent_tensor = [] 49 | tid = 0 50 | buffer = '' 51 | words = sent.lower().split() 52 | for i, t in enumerate(tokens): 53 | if t == '[CLS]' or t == '[SEP]': 54 | continue 55 | else: 56 | if t.startswith('##'): 57 | t = t[2:] 58 | buffer += t 59 | token_tensor.append(tensor[i, :]) 60 | if buffer == words[tid]: 61 | sent_tensor.append(np.stack(token_tensor).mean(axis=0)) 62 | token_tensor = [] 63 | buffer = '' 64 | tid += 1 65 | # print(len(valid)) 66 | # exit() 67 | if tid != len(words) or len(sent_tensor) != len(words): 68 | print(sent.split()) 69 | print(result[1]) 70 | batch.append(np.stack(sent_tensor)) 71 | return batch 72 | 73 | 74 | def generate_bert(path, output, embed_fun=embed_sum): 75 | total = 0 76 | with open(path) as src: 77 | batch = [] 78 | tensor = [] 79 | for line in src: 80 | line = line.strip() 81 | if len(line) == 0: 82 | continue 83 | batch.append(line) 84 | if len(batch) and len(batch) % 100 == 0: 85 | tensor.extend(embed_fun(batch)) 86 | total += len(batch) 87 | print(total) 88 | batch = [] 89 | if len(batch): 90 | tensor.extend(embed_fun(batch)) 91 | total += len(batch) 92 | print(total) 93 | with open(output, 'wb') as f: 94 | pickle.dump(tensor, f) 95 | 96 | 97 | if __name__ == '__main__': 98 | generate_bert('input.txt', 'output.pkl', embed_fun=embed_last_token) 99 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Created by .ignore support plugin (hsz.mobi) 2 | ### Python template 3 | # Byte-compiled / optimized / DLL files 4 | __pycache__/ 5 | *.py[cod] 6 | *$py.class 7 | 8 | # C extensions 9 | *.so 10 | 11 | # Distribution / packaging 12 | .Python 13 | build/ 14 | develop-eggs/ 15 | dist/ 16 | downloads/ 17 | eggs/ 18 | .eggs/ 19 | lib/ 20 | lib64/ 21 | parts/ 22 | sdist/ 23 | var/ 24 | wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | .hypothesis/ 50 | .pytest_cache/ 51 | 52 | # Translations 53 | *.mo 54 | *.pot 55 | 56 | # Django stuff: 57 | *.log 58 | local_settings.py 59 | db.sqlite3 60 | 61 | # Flask stuff: 62 | instance/ 63 | .webassets-cache 64 | 65 | # Scrapy stuff: 66 | .scrapy 67 | 68 | # Sphinx documentation 69 | docs/_build/ 70 | 71 | # PyBuilder 72 | target/ 73 | 74 | # Jupyter Notebook 75 | .ipynb_checkpoints 76 | 77 | # pyenv 78 | .python-version 79 | 80 | # celery beat schedule file 81 | celerybeat-schedule 82 | 83 | # SageMath parsed files 84 | *.sage.py 85 | 86 | # Environments 87 | .env 88 | .venv 89 | env/ 90 | venv/ 91 | ENV/ 92 | env.bak/ 93 | venv.bak/ 94 | 95 | # Spyder project settings 96 | .spyderproject 97 | .spyproject 98 | 99 | # Rope project settings 100 | .ropeproject 101 | 102 | # mkdocs documentation 103 | /site 104 | 105 | # mypy 106 | .mypy_cache/ 107 | ### JetBrains template 108 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm 109 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 110 | 111 | # User-specific stuff 112 | .idea/**/workspace.xml 113 | .idea/**/tasks.xml 114 | .idea/**/usage.statistics.xml 115 | .idea/**/dictionaries 116 | .idea/**/shelf 117 | 118 | # Sensitive or high-churn files 119 | .idea/**/dataSources/ 120 | .idea/**/dataSources.ids 121 | .idea/**/dataSources.local.xml 122 | .idea/**/sqlDataSources.xml 123 | .idea/**/dynamic.xml 124 | .idea/**/uiDesigner.xml 125 | .idea/**/dbnavigator.xml 126 | 127 | # Gradle 128 | .idea/**/gradle.xml 129 | .idea/**/libraries 130 | 131 | # Gradle and Maven with auto-import 132 | # When using Gradle or Maven with auto-import, you should exclude module files, 133 | # since they will be recreated, and may cause churn. Uncomment if using 134 | # auto-import. 135 | # .idea/modules.xml 136 | # .idea/*.iml 137 | # .idea/modules 138 | 139 | # CMake 140 | cmake-build-*/ 141 | 142 | # Mongo Explorer plugin 143 | .idea/**/mongoSettings.xml 144 | 145 | # File-based project format 146 | *.iws 147 | 148 | # IntelliJ 149 | out/ 150 | 151 | # mpeltonen/sbt-idea plugin 152 | .idea_modules/ 153 | 154 | # JIRA plugin 155 | atlassian-ide-plugin.xml 156 | 157 | # Cursive Clojure plugin 158 | .idea/replstate.xml 159 | 160 | # Crashlytics plugin (for Android Studio and IntelliJ) 161 | com_crashlytics_export_strings.xml 162 | crashlytics.properties 163 | crashlytics-build.properties 164 | fabric.properties 165 | 166 | # Editor-based Rest Client 167 | .idea/httpRequests 168 | .idea/ 169 | output.pkl 170 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------