{"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-recurrent-attention-network-for","title":"Hierarchical Recurrent Attention Network for Response Generation","arxiv_id":"1701.07149","date":"2017-01-25","proceeding":null,"authors":["Chen Xing","Wei Wu","Yu Wu","Ming Zhou","YaLou Huang","Wei-Ying Ma"],"abstract":"We study multi-turn response generation in chatbots where a response is\ngenerated according to a conversation context. Existing work has modeled the\nhierarchy of the context, but does not pay enough attention to the fact that\nwords and utterances in the context are differentially important. As a result,\nthey may lose important information in context and generate irrelevant\nresponses. We propose a hierarchical recurrent attention network (HRAN) to\nmodel both aspects in a unified framework. In HRAN, a hierarchical attention\nmechanism attends to important parts within and among utterances with word\nlevel attention and utterance level attention respectively. With the word level\nattention, hidden vectors of a word level encoder are synthesized as utterance\nvectors and fed to an utterance level encoder to construct hidden\nrepresentations of the context. The hidden vectors of the context are then\nprocessed by the utterance level attention and formed as context vectors for\ndecoding the response. Empirical studies on both automatic evaluation and human\njudgment show that HRAN can significantly outperform state-of-the-art models\nfor multi-turn response generation.","url_abs":"http://arxiv.org/abs/1701.07149v1","url_pdf":"http://arxiv.org/pdf/1701.07149v1.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-recurrent-attention-network-for","repo_url":"https://github.com/LynetteXing1991/HRAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"response-generation","task_name":"Response Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.07149","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}