{"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/technology-assisted-reviews-finding-the-last","title":"Technology Assisted Reviews: Finding the Last Few Relevant Documents by Asking Yes/No Questions to Reviewers","arxiv_id":"1810.05414","date":"2018-10-12","proceeding":null,"authors":["Zou Jie","Li Dan","Kanoulas Evangelos"],"abstract":"The goal of a technology-assisted review is to achieve high recall with low\nhuman effort. Continuous active learning algorithms have demonstrated good\nperformance in locating the majority of relevant documents in a collection,\nhowever their performance is reaching a plateau when 80\\%-90\\% of them has been\nfound. Finding the last few relevant documents typically requires exhaustively\nreviewing the collection. In this paper, we propose a novel method to identify\nthese last few, but significant, documents efficiently. Our method makes the\nhypothesis that entities carry vital information in documents, and that\nreviewers can answer questions about the presence or absence of an entity in\nthe missing relevance documents. Based on this we devise a sequential Bayesian\nsearch method that selects the optimal sequence of questions to ask. The\nexperimental results show that our proposed method can greatly improve\nperformance requiring less reviewing effort.","url_abs":"http://arxiv.org/abs/1810.05414v1","url_pdf":"http://arxiv.org/pdf/1810.05414v1.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":"technology-assisted-reviews-finding-the-last","repo_url":"https://github.com/jiezou0806/SBSTAR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}