{"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/multi-task-learning-with-multi-view-attention","title":"Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering","arxiv_id":"1812.02354","date":"2018-12-06","proceeding":null,"authors":["Yang Deng","Yuexiang Xie","Yaliang Li","Min Yang","Nan Du","Wei Fan","Kai Lei","Ying Shen"],"abstract":"Answer selection and knowledge base question answering (KBQA) are two\nimportant tasks of question answering (QA) systems. Existing methods solve\nthese two tasks separately, which requires large number of repetitive work and\nneglects the rich correlation information between tasks. In this paper, we\ntackle answer selection and KBQA tasks simultaneously via multi-task learning\n(MTL), motivated by the following motivations. First, both answer selection and\nKBQA can be regarded as a ranking problem, with one at text-level while the\nother at knowledge-level. Second, these two tasks can benefit each other:\nanswer selection can incorporate the external knowledge from knowledge base\n(KB), while KBQA can be improved by learning contextual information from answer\nselection. To fulfill the goal of jointly learning these two tasks, we propose\na novel multi-task learning scheme that utilizes multi-view attention learned\nfrom various perspectives to enable these tasks to interact with each other as\nwell as learn more comprehensive sentence representations. The experiments\nconducted on several real-world datasets demonstrate the effectiveness of the\nproposed method, and the performance of answer selection and KBQA is improved.\nAlso, the multi-view attention scheme is proved to be effective in assembling\nattentive information from different representational perspectives.","url_abs":"http://arxiv.org/abs/1812.02354v1","url_pdf":"http://arxiv.org/pdf/1812.02354v1.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":"multi-task-learning-with-multi-view-attention","repo_url":"https://github.com/dengyang17/MTQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"multi-task-learning-with-multi-view-attention","repo_url":"https://github.com/dengyang17/dengyang17.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"answer-selection","task_name":"Answer Selection"},{"task_slug":"knowledge-base-question-answering","task_name":"Knowledge Base Question Answering"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.02354","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}