{"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/exploring-question-understanding-and","title":"Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering","arxiv_id":"1703.04617","date":"2017-03-14","proceeding":null,"authors":["Junbei Zhang","Xiaodan Zhu","Qian Chen","Li-Rong Dai","Si Wei","Hui Jiang"],"abstract":"The last several years have seen intensive interest in exploring\nneural-network-based models for machine comprehension (MC) and question\nanswering (QA). In this paper, we approach the problems by closely modelling\nquestions in a neural network framework. We first introduce syntactic\ninformation to help encode questions. We then view and model different types of\nquestions and the information shared among them as an adaptation task and\nproposed adaptation models for them. On the Stanford Question Answering Dataset\n(SQuAD), we show that these approaches can help attain better results over a\ncompetitive baseline.","url_abs":"http://arxiv.org/abs/1703.04617v2","url_pdf":"http://arxiv.org/pdf/1703.04617v2.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":[],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"jNet (ensemble)","rank_in_archive_order":139,"of":213,"metrics":{"EM":"73.010","F1":"81.517"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"jNet (single model)","rank_in_archive_order":160,"of":213,"metrics":{"EM":"70.607","F1":"79.821"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"jNet (TreeLSTM adaptation, QTLa, K=100)","rank_in_archive_order":39,"of":55,"metrics":{"EM":"69.10","F1":"78.38"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}