{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/emrqa-a-large-corpus-for-question-answering","title":"emrQA: A Large Corpus for Question Answering on Electronic Medical Records","arxiv_id":"1809.00732","date":"2018-09-03","proceeding":"EMNLP 2018 10","authors":["Anusri Pampari","Preethi Raghavan","Jennifer Liang","Jian Peng"],"abstract":"We propose a novel methodology to generate domain-specific large-scale\nquestion answering (QA) datasets by re-purposing existing annotations for other\nNLP tasks. We demonstrate an instance of this methodology in generating a\nlarge-scale QA dataset for electronic medical records by leveraging existing\nexpert annotations on clinical notes for various NLP tasks from the community\nshared i2b2 datasets. The resulting corpus (emrQA) has 1 million\nquestion-logical form and 400,000+ question-answer evidence pairs. We\ncharacterize the dataset and explore its learning potential by training\nbaseline models for question to logical form and question to answer mapping.","url_abs":"http://arxiv.org/abs/1809.00732v1","url_pdf":"http://arxiv.org/pdf/1809.00732v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"emrqa-a-large-corpus-for-question-answering","repo_url":"https://github.com/panushri25/emrQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"emrqa-a-large-corpus-for-question-answering","repo_url":"https://github.com/xiangyue9607/CliniRC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"emrqa-a-large-corpus-for-question-answering","repo_url":"https://github.com/YIKUAN8/Clinical-Longformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"emrqa","name":"emrQA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.00732","atlas_url":"https://app.syntology.ai/?focus=1809.00732","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}