{"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/a-corpus-with-multi-level-annotations-of","title":"A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature","arxiv_id":"1806.04185","date":"2018-06-11","proceeding":"ACL 2018 7","authors":["Benjamin Nye","Junyi Jessy Li","Roma Patel","Yinfei Yang","Iain J. Marshall","Ani Nenkova","Byron C. Wallace"],"abstract":"We present a corpus of 5,000 richly annotated abstracts of medical articles\ndescribing clinical randomized controlled trials. Annotations include\ndemarcations of text spans that describe the Patient population enrolled, the\nInterventions studied and to what they were Compared, and the Outcomes measured\n(the `PICO' elements). These spans are further annotated at a more granular\nlevel, e.g., individual interventions within them are marked and mapped onto a\nstructured medical vocabulary. We acquired annotations from a diverse set of\nworkers with varying levels of expertise and cost. We describe our data\ncollection process and the corpus itself in detail. We then outline a set of\nchallenging NLP tasks that would aid searching of the medical literature and\nthe practice of evidence-based medicine.","url_abs":"http://arxiv.org/abs/1806.04185v1","url_pdf":"http://arxiv.org/pdf/1806.04185v1.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":"a-corpus-with-multi-level-annotations-of","repo_url":"https://github.com/devkotasabin/EBM-NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-corpus-with-multi-level-annotations-of","repo_url":"https://github.com/jetsunwhitton/rct-art","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"pico","task_name":"PICO"},{"task_slug":"participant-intervention-comparison-outcome","task_name":"Participant Intervention Comparison Outcome Extraction"}],"methods":[],"datasets_introduced":[{"slug":"ebm-nlp","name":"EBM-NLP","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/participant-intervention-comparison-outcome","task":"Participant Intervention Comparison Outcome Extraction","dataset":"EBM-NLP","model":"bi-LSTM","rank_in_archive_order":5,"of":5,"metrics":{"F1":"66.30"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.04185","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}