[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-153341-105":59,"doc-detail-153341-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","long-time-no-see-open-domain-conversation-with-long-term-persona-memory-2022-findings-of-the-association-for-computational-linguistics-acl-2022","Long Time No See! Open-Domain Conversation with Long-Term Persona - Memory - 2022 Findings of the Association for Computational Linguistics (ACL 2022)","","Most open-domain dialogue models struggle in long-term human-bot conversations because they cannot effectively understand and memorize dialogue history. To address this gap, the paper introduces the Long-term Memory Conversation (LeMon) task, builds the DuLeMon dataset, and proposes PLATO-LTM, a generation framework with a long-term memory mechanism. The mechanism extracts and continuously updates mutual persona memory for both user and bot in real time, improving long-dialogue consistency and engagement.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/long-time-no-see-open-domain-conversation-with-long-term-persona-memory-2022-findings-of-the-association-for-computational-linguistics-acl-2022/153341/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/long-time-no-see-open-domain-conversation-with-long-term-persona-memory-2022-findings-of-the-association-for-computational-linguistics-acl-2022/153341.png","ImageObject",300,407,{"name":92,"@type":93},"วิน","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-20","2026-08-27",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"为什么现有开放域对话模型在长期人机对话中表现较差？","Question",{"text":112,"@type":113},"主要原因是模型缺乏理解并记忆长期对话历史信息的能力，无法稳定维持用户与机器之间的长期关联。","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"论文提出了哪些关键方法来解决长期人格记忆问题？",{"text":117,"@type":113},"提出了Long-term Memory Conversation（LeMon）任务，构建DuLeMon数据集，并开发带长时记忆机制的PLATO-LTM对话生成框架。",{"name":119,"@type":110,"acceptedAnswer":120},"PLATO-LTM如何在对话过程中管理并更新长期人格信息？",{"text":121,"@type":113},"PLATO-LTM能够在实时对话中抽取双方人格信息，并持续写入与更新长期人格记忆，从而支持后续更一致、更具参与感的对话。","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},153341,1787874022,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":41},2336475104736,"https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222","Long Time No See! Open-Domain Conversation with Long-Term Persona  \nMemory  \nXinchao Xu1∗, Zhibin Gou1,2∗, Wenquan Wu1 , Zheng-Yu Niu1 , Hua Wu1 , Haifeng Wang1 and Shihang Wang3  \n1Baidu Inc., China  \n2 School of Computer Science, Beijing University of Posts and Telecommunications  \n3 Columbia University  \n{xinchaoxu,wuwenquan01,niuzhengyu,wu_hua,[wanghaifeng}@baidu.com](wanghaifeng}@baidu.com)[ ](wanghaifeng}@baidu.com)[zebgou@gmail.com](zebgou@gmail.com), [sw3275@columbia.edu](sw3275@columbia.edu)  \nAbstract  \nMost of the open-domain dialogue models tend to perform poorly in the setting of long-term human-bot conversations. The possible reason is that they lack the capability of understanding and memorizing long-term dialogue history information. To address this issue, we present a novel task of Long-term Memory Conversation (LeMon) and then build a new dialogue dataset DuLeMon and a dialogue generation framework PLATO-LTM with a Long-Term Memory (LTM) mechanism. This LTM mechanism enables our system to accurately extract and continuously update long-term persona memory without requiring multiple-session dialogue datasets for model training. To our knowledge, this is the first attempt to conduct real-time dynamic management of persona information of both parties, including the user and the bot. Results on DuLeMon indicate that PLATO-LTM can significantly outperform baselines in terms of long-term dialogue consistency, leading to better dialogue engagingness 1.  \n1 Introduction  \nPersona is crucial for open-domain dialogue systems to establish long-term intimacy with users (Huang et al., 2020) . Existing persona dialogue datasets such as PersonaChat (Zhang et al., 2018 ; Dinan et al., 2019) and models (Li et al., 2016a ; Zhang et al., 2017 ; Qian et al., 2018) have greatly facilitated the chatbot with configurable and persistent personalities.  \nNevertheless, current open-domain dialogue systems still cannot build a long-term connection with humans. The possible reason is that they lack the capability of understanding and memorizing longterm dialogue history information, which we called  \n∗ Equal contribution. The work was done when Zhibin Gou and Shihang Wang were doing internship at Baidu.  \n1Our data and codes are released at [https:](https:)//[github.com/PaddlePaddle/Research/tree/](github.com/PaddlePaddle/Research/tree/)[ ](github.com/PaddlePaddle/Research/tree/)master/NLP/ACL2022-DuLeMon  \nUser   Chatbot  \nTrigger  \nTrigger  \nFigure 1: A sample of long-term conversation with memory. At first, the chat partner is not familiar with each other, so the goal is to get to know each other; Then, after multiple sessions, the chatbot already has a certain understanding and memory of the user’s persona and its own persona, making the deep chat possible.  \nlong-term persona ability. Remembering and actively utilizing the user’s persona increases engagingness and contributes to long-term friendships between chatbot and user (Campos et al., 2018) . Without this ability, the current state-of-the-art models, such as Meena (Adiwardana et al., 2020), Blender (Roller et al., 2021), and PLATO (Bao et al., 2020), tend to talk to people like strangers in long-term conversations.  \nDespite the importance and challenge of utilizing long-term persona in open-domain dialogue, as far as we know, the long-term persona ability of large-scale models is less studied due to a lack of both task design and corresponding dataset. Previous long-term persona dialogue systems (Kim et al., 2014 ; Bang et al., 2015) are mainly rule-based systems without large-scale pre-training models, in which researchers proposed various episodic memory architectures to extract, store and manage rel-  \n2639  \nFindings of the Association for Computational Linguistics: ACL 2022 , pages 2639-2650 May 22-27, 2022 􀀍c2022 Association for Computational Linguistics  \nevant facts in prior interactions for use in future dialogs (Campos et al., 2018) .  \nIn addition, existing person","cbCaibMptnl5xoHN","https://ap.wps.com/l/cbCaibMptnl5xoHN","pdf",482337,12,"English","# Introduction\n## Long-term persona ability and its challenges\n## Related work: persona dialogue datasets and models\n## Proposed LeMon task and DuLeMon dataset\n## PLATO-LTM framework with long-term memory","[{\"question\":\"为什么现有开放域对话模型在长期人机对话中表现较差？\",\"answer\":\"主要原因是模型缺乏理解并记忆长期对话历史信息的能力，无法稳定维持用户与机器之间的长期关联。\"},{\"question\":\"论文提出了哪些关键方法来解决长期人格记忆问题？\",\"answer\":\"提出了Long-term Memory Conversation（LeMon）任务，构建DuLeMon数据集，并开发带长时记忆机制的PLATO-LTM对话生成框架。\"},{\"question\":\"PLATO-LTM如何在对话过程中管理并更新长期人格信息？\",\"answer\":\"PLATO-LTM能够在实时对话中抽取双方人格信息，并持续写入与更新长期人格记忆，从而支持后续更一致、更具参与感的对话。\"}]","Long Time No See! Open-Domain Conversation with Long-Term Persona - Memory - 2022 Findings of the Association for Computational Linguistics (ACL 2022) | PDF"]