{"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/adaptive-document-retrieval-for-deep-question","title":"Adaptive Document Retrieval for Deep Question Answering","arxiv_id":"1808.06528","date":"2018-08-20","proceeding":"EMNLP 2018 10","authors":["Bernhard Kratzwald","Stefan Feuerriegel"],"abstract":"State-of-the-art systems in deep question answering proceed as follows: (1)\nan initial document retrieval selects relevant documents, which (2) are then\nprocessed by a neural network in order to extract the final answer. Yet the\nexact interplay between both components is poorly understood, especially\nconcerning the number of candidate documents that should be retrieved. We show\nthat choosing a static number of documents -- as used in prior research --\nsuffers from a noise-information trade-off and yields suboptimal results. As a\nremedy, we propose an adaptive document retrieval model. This learns the\noptimal candidate number for document retrieval, conditional on the size of the\ncorpus and the query. We report extensive experimental results showing that our\nadaptive approach outperforms state-of-the-art methods on multiple benchmark\ndatasets, as well as in the context of corpora with variable sizes.","url_abs":"http://arxiv.org/abs/1808.06528v1","url_pdf":"http://arxiv.org/pdf/1808.06528v1.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":"adaptive-document-retrieval-for-deep-question","repo_url":"https://github.com/bernhard2202/adaptive-ir-for-qa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.06528","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}