{"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/efficient-and-robust-question-answering-from","title":"Efficient and Robust Question Answering from Minimal Context over Documents","arxiv_id":"1805.08092","date":"2018-05-21","proceeding":"ACL 2018 7","authors":["Sewon Min","Victor Zhong","Richard Socher","Caiming Xiong"],"abstract":"Neural models for question answering (QA) over documents have achieved\nsignificant performance improvements. Although effective, these models do not\nscale to large corpora due to their complex modeling of interactions between\nthe document and the question. Moreover, recent work has shown that such models\nare sensitive to adversarial inputs. In this paper, we study the minimal\ncontext required to answer the question, and find that most questions in\nexisting datasets can be answered with a small set of sentences. Inspired by\nthis observation, we propose a simple sentence selector to select the minimal\nset of sentences to feed into the QA model. Our overall system achieves\nsignificant reductions in training (up to 15 times) and inference times (up to\n13 times), with accuracy comparable to or better than the state-of-the-art on\nSQuAD, NewsQA, TriviaQA and SQuAD-Open. Furthermore, our experimental results\nand analyses show that our approach is more robust to adversarial inputs.","url_abs":"http://arxiv.org/abs/1805.08092v1","url_pdf":"http://arxiv.org/pdf/1805.08092v1.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":"efficient-and-robust-question-answering-from","repo_url":"https://github.com/SatyamSoni23/Smart-Question-Answering-System-on-Document","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-newsqa","task":"Question Answering","dataset":"NewsQA","model":"MINIMAL(Dyn)","rank_in_archive_order":13,"of":18,"metrics":{"EM":"50.1","F1":"63.2"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.08092","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}