{"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/dataset-and-neural-recurrent-sequence","title":"Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering","arxiv_id":"1607.06275","date":"2016-07-21","proceeding":null,"authors":["Peng Li","Wei Li","Zhengyan He","Xuguang Wang","Ying Cao","Jie zhou","Wei Xu"],"abstract":"While question answering (QA) with neural network, i.e. neural QA, has\nachieved promising results in recent years, lacking of large scale real-word QA\ndataset is still a challenge for developing and evaluating neural QA system. To\nalleviate this problem, we propose a large scale human annotated real-world QA\ndataset WebQA with more than 42k questions and 556k evidences. As existing\nneural QA methods resolve QA either as sequence generation or\nclassification/ranking problem, they face challenges of expensive softmax\ncomputation, unseen answers handling or separate candidate answer generation\ncomponent. In this work, we cast neural QA as a sequence labeling problem and\npropose an end-to-end sequence labeling model, which overcomes all the above\nchallenges. Experimental results on WebQA show that our model outperforms the\nbaselines significantly with an F1 score of 74.69% with word-based input, and\nthe performance drops only 3.72 F1 points with more challenging character-based\ninput.","url_abs":"http://arxiv.org/abs/1607.06275v2","url_pdf":"http://arxiv.org/pdf/1607.06275v2.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":"dataset-and-neural-recurrent-sequence","repo_url":"https://github.com/Hanlard/Bert-for-WebQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dataset-and-neural-recurrent-sequence","repo_url":"https://github.com/OpenNLPhub/WebQA-Using-DGCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dataset-and-neural-recurrent-sequence","repo_url":"https://github.com/WangJiuniu/SRQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"answer-generation","task_name":"Answer Generation"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1607.06275","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}