├── Figure.png ├── README.md ├── code ├── eda.py ├── get_bert_embeddings.py ├── methods.py ├── split_category_dataset.py ├── split_class_dataset.py ├── test_category_knn.py ├── test_category_svm.py └── test_class_knn.py ├── data ├── Original CSVs │ ├── .DS_Store │ ├── All_Matched_Questions.csv │ ├── Bing_Dataset.csv │ ├── CDC_Dataset.csv │ ├── CNN_Dataset.csv │ ├── COVID-QA_Dataset.csv │ ├── FDA_Dataset.csv │ ├── IDPH_Dataset.csv │ ├── John-Hopkins_Dataset.csv │ ├── KeywordTool_Dataset.csv │ ├── Quora_Dataset.csv │ ├── UN_Dataset.csv │ ├── WJLA_Dataset.csv │ ├── Yahoo-Answers_Dataset.csv │ └── Yahoo_Dataset.csv ├── PDFs │ ├── Bing Dataset.pdf │ ├── CDC Dataset.pdf │ ├── CNN Dataset.pdf │ ├── FDA Dataset.pdf │ ├── GitHub Dataset.pdf │ ├── Google Dataset 1.pdf │ ├── Google Dataset 2.pdf │ ├── Google Dataset 3.pdf │ ├── Google Dataset 4.pdf │ ├── Google Dataset 5.pdf │ ├── Google Dataset 6.pdf │ ├── IDPH Dataset.pdf │ ├── John-Hopkins Dataset.pdf │ ├── Quora.txt │ ├── UN Dataset.pdf │ ├── WJLA Dataset.pdf │ └── Yahoo-Answers.txt ├── TSVs │ ├── .DS_Store │ ├── All_Matched_Questions.tsv │ ├── Bing_Dataset.tsv │ ├── CDC_Dataset.tsv │ ├── CNN_Dataset.tsv │ ├── COVID-QA_Dataset.tsv │ ├── FDA_Dataset.tsv │ ├── Generated_Questions.tsv │ ├── IDPH_Dataset.tsv │ ├── John-Hopkins_Dataset.tsv │ ├── KeywordTool_Dataset.tsv │ ├── Quora_Dataset.tsv │ ├── UN_Dataset.tsv │ ├── WJLA_Dataset.tsv │ ├── Yahoo-Answers_Dataset.tsv │ └── Yahoo_Dataset.tsv ├── final_master_dataset.csv └── zDatasetDocumentation.txt ├── dataset_categories ├── question_embeddings_pooled.pickle ├── testA.csv ├── testB.csv ├── train20.csv └── train20_augmented.csv ├── dataset_classes ├── question_embeddings_pooled.pickle ├── testA.csv ├── testB.csv ├── train3.csv └── train3_augmented.csv └── final_master_dataset.csv /Figure.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/Figure.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/README.md -------------------------------------------------------------------------------- /code/eda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/code/eda.py -------------------------------------------------------------------------------- /code/get_bert_embeddings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/code/get_bert_embeddings.py -------------------------------------------------------------------------------- /code/methods.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/code/methods.py -------------------------------------------------------------------------------- /code/split_category_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/code/split_category_dataset.py -------------------------------------------------------------------------------- /code/split_class_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/code/split_class_dataset.py -------------------------------------------------------------------------------- /code/test_category_knn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/code/test_category_knn.py -------------------------------------------------------------------------------- /code/test_category_svm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/code/test_category_svm.py -------------------------------------------------------------------------------- /code/test_class_knn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/code/test_class_knn.py -------------------------------------------------------------------------------- /data/Original CSVs/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/.DS_Store -------------------------------------------------------------------------------- /data/Original CSVs/All_Matched_Questions.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/All_Matched_Questions.csv -------------------------------------------------------------------------------- /data/Original CSVs/Bing_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/Bing_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/CDC_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/CDC_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/CNN_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/CNN_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/COVID-QA_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/COVID-QA_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/FDA_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/FDA_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/IDPH_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/IDPH_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/John-Hopkins_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/John-Hopkins_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/KeywordTool_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/KeywordTool_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/Quora_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/Quora_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/UN_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/UN_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/WJLA_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/WJLA_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/Yahoo-Answers_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/Yahoo-Answers_Dataset.csv -------------------------------------------------------------------------------- /data/Original CSVs/Yahoo_Dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/Original CSVs/Yahoo_Dataset.csv -------------------------------------------------------------------------------- /data/PDFs/Bing Dataset.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/Bing Dataset.pdf -------------------------------------------------------------------------------- /data/PDFs/CDC Dataset.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/CDC Dataset.pdf -------------------------------------------------------------------------------- /data/PDFs/CNN Dataset.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/CNN Dataset.pdf -------------------------------------------------------------------------------- /data/PDFs/FDA Dataset.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/FDA Dataset.pdf -------------------------------------------------------------------------------- /data/PDFs/GitHub Dataset.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/GitHub Dataset.pdf -------------------------------------------------------------------------------- /data/PDFs/Google Dataset 1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/Google Dataset 1.pdf -------------------------------------------------------------------------------- /data/PDFs/Google Dataset 2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/Google Dataset 2.pdf -------------------------------------------------------------------------------- /data/PDFs/Google Dataset 3.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/Google Dataset 3.pdf -------------------------------------------------------------------------------- /data/PDFs/Google Dataset 4.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/Google Dataset 4.pdf -------------------------------------------------------------------------------- /data/PDFs/Google Dataset 5.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/Google Dataset 5.pdf -------------------------------------------------------------------------------- /data/PDFs/Google Dataset 6.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/Google Dataset 6.pdf -------------------------------------------------------------------------------- /data/PDFs/IDPH Dataset.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/IDPH Dataset.pdf -------------------------------------------------------------------------------- /data/PDFs/John-Hopkins Dataset.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/John-Hopkins Dataset.pdf -------------------------------------------------------------------------------- /data/PDFs/Quora.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/Quora.txt -------------------------------------------------------------------------------- /data/PDFs/UN Dataset.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/UN Dataset.pdf -------------------------------------------------------------------------------- /data/PDFs/WJLA Dataset.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/WJLA Dataset.pdf -------------------------------------------------------------------------------- /data/PDFs/Yahoo-Answers.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/PDFs/Yahoo-Answers.txt -------------------------------------------------------------------------------- /data/TSVs/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/.DS_Store -------------------------------------------------------------------------------- /data/TSVs/All_Matched_Questions.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/All_Matched_Questions.tsv -------------------------------------------------------------------------------- /data/TSVs/Bing_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/Bing_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/CDC_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/CDC_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/CNN_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/CNN_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/COVID-QA_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/COVID-QA_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/FDA_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/FDA_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/Generated_Questions.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/Generated_Questions.tsv -------------------------------------------------------------------------------- /data/TSVs/IDPH_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/IDPH_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/John-Hopkins_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/John-Hopkins_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/KeywordTool_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/KeywordTool_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/Quora_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/Quora_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/UN_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/UN_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/WJLA_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/WJLA_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/Yahoo-Answers_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/Yahoo-Answers_Dataset.tsv -------------------------------------------------------------------------------- /data/TSVs/Yahoo_Dataset.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/TSVs/Yahoo_Dataset.tsv -------------------------------------------------------------------------------- /data/final_master_dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/final_master_dataset.csv -------------------------------------------------------------------------------- /data/zDatasetDocumentation.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/data/zDatasetDocumentation.txt -------------------------------------------------------------------------------- /dataset_categories/question_embeddings_pooled.pickle: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_categories/question_embeddings_pooled.pickle -------------------------------------------------------------------------------- /dataset_categories/testA.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_categories/testA.csv -------------------------------------------------------------------------------- /dataset_categories/testB.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_categories/testB.csv -------------------------------------------------------------------------------- /dataset_categories/train20.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_categories/train20.csv -------------------------------------------------------------------------------- /dataset_categories/train20_augmented.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_categories/train20_augmented.csv -------------------------------------------------------------------------------- /dataset_classes/question_embeddings_pooled.pickle: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_classes/question_embeddings_pooled.pickle -------------------------------------------------------------------------------- /dataset_classes/testA.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_classes/testA.csv -------------------------------------------------------------------------------- /dataset_classes/testB.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_classes/testB.csv -------------------------------------------------------------------------------- /dataset_classes/train3.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_classes/train3.csv -------------------------------------------------------------------------------- /dataset_classes/train3_augmented.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/dataset_classes/train3_augmented.csv -------------------------------------------------------------------------------- /final_master_dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JerryWeiAI/COVID-Q/HEAD/final_master_dataset.csv --------------------------------------------------------------------------------