{"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/smarnet-teaching-machines-to-read-and","title":"Smarnet: Teaching Machines to Read and Comprehend Like Human","arxiv_id":"1710.02772","date":"2017-10-08","proceeding":null,"authors":["Zheqian Chen","Rongqin Yang","Bin Cao","Zhou Zhao","Deng Cai","Xiaofei He"],"abstract":"Machine Comprehension (MC) is a challenging task in Natural Language\nProcessing field, which aims to guide the machine to comprehend a passage and\nanswer the given question. Many existing approaches on MC task are suffering\nthe inefficiency in some bottlenecks, such as insufficient lexical\nunderstanding, complex question-passage interaction, incorrect answer\nextraction and so on. In this paper, we address these problems from the\nviewpoint of how humans deal with reading tests in a scientific way.\nSpecifically, we first propose a novel lexical gating mechanism to dynamically\ncombine the words and characters representations. We then guide the machines to\nread in an interactive way with attention mechanism and memory network. Finally\nwe add a checking layer to refine the answer for insurance. The extensive\nexperiments on two popular datasets SQuAD and TriviaQA show that our method\nexceeds considerable performance than most state-of-the-art solutions at the\ntime of submission.","url_abs":"http://arxiv.org/abs/1710.02772v1","url_pdf":"http://arxiv.org/pdf/1710.02772v1.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"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"smarnet (single model)","rank_in_archive_order":149,"of":213,"metrics":{"EM":"71.415","F1":"80.160"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"Smarnet","rank_in_archive_order":33,"of":55,"metrics":{"EM":"71.362","F1":"80.183"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}