{"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/hierarchical-memory-networks-for-answer","title":"Hierarchical Memory Networks for Answer Selection on Unknown Words","arxiv_id":"1609.08843","date":"2016-09-28","proceeding":"COLING 2016 12","authors":["Jiaming Xu","Jing Shi","Yiqun Yao","Suncong Zheng","Bo Xu"],"abstract":"Recently, end-to-end memory networks have shown promising results on Question\nAnswering task, which encode the past facts into an explicit memory and perform\nreasoning ability by making multiple computational steps on the memory.\nHowever, memory networks conduct the reasoning on sentence-level memory to\noutput coarse semantic vectors and do not further take any attention mechanism\nto focus on words, which may lead to the model lose some detail information,\nespecially when the answers are rare or unknown words. In this paper, we\npropose a novel Hierarchical Memory Networks, dubbed HMN. First, we encode the\npast facts into sentence-level memory and word-level memory respectively. Then,\n(k)-max pooling is exploited following reasoning module on the sentence-level\nmemory to sample the (k) most relevant sentences to a question and feed these\nsentences into attention mechanism on the word-level memory to focus the words\nin the selected sentences. Finally, the prediction is jointly learned over the\noutputs of the sentence-level reasoning module and the word-level attention\nmechanism. The experimental results demonstrate that our approach successfully\nconducts answer selection on unknown words and achieves a better performance\nthan memory networks.","url_abs":"http://arxiv.org/abs/1609.08843v1","url_pdf":"http://arxiv.org/pdf/1609.08843v1.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":"hierarchical-memory-networks-for-answer","repo_url":"https://github.com/jacoxu/HMN4QA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"answer-selection","task_name":"Answer Selection"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}