{"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/ranking-paragraphs-for-improving-answer","title":"Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering","arxiv_id":"1810.00494","date":"2018-10-01","proceeding":"EMNLP 2018 10","authors":["Jinhyuk Lee","Seongjun Yun","Hyunjae Kim","Miyoung Ko","Jaewoo Kang"],"abstract":"Recently, open-domain question answering (QA) has been combined with machine\ncomprehension models to find answers in a large knowledge source. As\nopen-domain QA requires retrieving relevant documents from text corpora to\nanswer questions, its performance largely depends on the performance of\ndocument retrievers. However, since traditional information retrieval systems\nare not effective in obtaining documents with a high probability of containing\nanswers, they lower the performance of QA systems. Simply extracting more\ndocuments increases the number of irrelevant documents, which also degrades the\nperformance of QA systems. In this paper, we introduce Paragraph Ranker which\nranks paragraphs of retrieved documents for a higher answer recall with less\nnoise. We show that ranking paragraphs and aggregating answers using Paragraph\nRanker improves performance of open-domain QA pipeline on the four open-domain\nQA datasets by 7.8% on average.","url_abs":"http://arxiv.org/abs/1810.00494v1","url_pdf":"http://arxiv.org/pdf/1810.00494v1.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":"ranking-paragraphs-for-improving-answer","repo_url":"https://github.com/yongqyu/ranking_paragraphs_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.00494","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}