{"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/dual-ask-answer-network-for-machine-reading","title":"Dual Ask-Answer Network for Machine Reading Comprehension","arxiv_id":"1809.01997","date":"2018-09-06","proceeding":null,"authors":["Han Xiao","Feng Wang","Jian-Feng Yan","Jingyao Zheng"],"abstract":"There are three modalities in the reading comprehension setting: question,\nanswer and context. The task of question answering or question generation aims\nto infer an answer or a question when given the counterpart based on context.\nWe present a novel two-way neural sequence transduction model that connects\nthree modalities, allowing it to learn two tasks simultaneously and mutually\nbenefit one another. During training, the model receives\nquestion-context-answer triplets as input and captures the cross-modal\ninteraction via a hierarchical attention process. Unlike previous joint\nlearning paradigms that leverage the duality of question generation and\nquestion answering at data level, we solve such dual tasks at the architecture\nlevel by mirroring the network structure and partially sharing components at\ndifferent layers. This enables the knowledge to be transferred from one task to\nanother, helping the model to find a general representation for each modality.\nThe evaluation on four public datasets shows that our dual-learning model\noutperforms the mono-learning counterpart as well as the state-of-the-art joint\nmodels on both question answering and question generation tasks.","url_abs":"http://arxiv.org/abs/1809.01997v2","url_pdf":"http://arxiv.org/pdf/1809.01997v2.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":"dual-ask-answer-network-for-machine-reading","repo_url":"https://github.com/hanxiao/daanet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.01997","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}