[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-199755-en":3,"doc-seo-199755-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},199755,8796096645457,"Arica Lee","https://ap-avatar.wpscdn.com/avatar/800003749518d68ffe3?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345340919836971",8,"Research & Report","DialDoc 2021 - The 1st Workshop on Document-grounded Dialogue and Conversational Question Answering - Proceedings","DialDoc 2021 workshop proceedings compile research on document-grounded dialogue and conversational question answering, emphasizing systems whose responses are grounded in relevant content from associated documents. The preface explains the need for personal assistive conversational systems that dynamically access heterogeneous document knowledge across unstructured text, semi-structured tables/lists, multimedia, and structured data on the web. The Shared Task targets goal-oriented information-seeking dialogue with two subtasks covering grounding-span prediction and natural-language response generation, plus reported evaluation results and team submissions.","DialDoc 2021  \nThe 1st Workshop on Document-grounded Dialogue and Conversational Question Answering  \nProceedings of the Workshop  \nAugust 5, 2021 Bangkok, Thailand (online)  \n©2021 The Association for Computational Linguistics and The Asian Federation of Natural Language Processing  \nOrder copies of this and other ACL proceedings from:  \nAssociation for Computational Linguistics (ACL) 209 N. Eighth Street  \nStroudsburg, PA 18360  \nUSA  \nTel: +1-570-476-8006  \nFax: +1-570-476-0860  \n[acl@aclweb.org](acl@aclweb.org)  \nISBN 978-1-954085-68-8  \nPreface  \nDialDoc Workshop focuses on Document-grounded Dialogue and Conversational Question Answering where system responses or answers are based on the relevant content in the associated documents. Such dialogue and conversational question answering systems have the potential to access heterogeneous knowledge in document content dynamically via natural language interactions. In addition, there is avast amount of written and visual document content created by individuals and organizations to present their knowledge to the world in broad applications. Thus, there is a substantial demand of building personal assistive conversational systems based on documents in many different domains. This area also attracts great attentions from researchers and practitioners in various fields.  \nThere are significant individual research threads that show promises in dialogue and QA models over different kinds of knowledge in document content, including (1) unstructured content such as text passages; (2) semi-structured content such as tables or lists; (3) multimedia such as images and videos with associated textual descriptions; (4) or structured data specified by schema such as RDFa or Microdata in the webpages. The purpose of this workshop is to invite researchers to bring their individual perspectives on the document-grounded dialogue and conversational question answering and advance the related AI research in joint effort. We also organize a Shared Task on modeling goal-oriented information-seeking dialogues that are grounded in the associated documents.  \nThis Shared Task focuses on building goal-oriented information-seeking conversation systems. The goal is to teach a dialogue system to identify the most relevant knowledge in the given document for generating agent responses in natural language. It includes two subtasks: the first subtask is to predict the grounding span for next agent response given the context; the second subtask is to generate agent response in natural language given the context. There are a total of 23 teams that participated Dev-Test phase. For final test phrase, 11 teams submitted to the leaderboard of Subtask 1, and 9 teams submitted to the leaderboard of Subtask 2 . Many submissions outperform baseline significantly. For the first task, the best system achieved 67.1 Exact Match and 76.3 F1 score. For the second subtask, the best system achieved 41.1 SacreBLEU score and highest rank by human evaluation.  \nIn this workshop, we have research track and technical system track for Shared Task. There are a total 22 submissions, including 14 submissions to research track and 8 submissions to technical system track, among which, there are 5 non-archival submissions. The workshop program features all 19 accepted papers with another 8 ACL finding papers from ACL main conference. The paper presentations are either as posters or talks in virtual format. We are also fortunate to have great invited talks by Jonathan Berant, Danqi Chen, Dilek Hakkani-Tur, Verena Rieser, Jason Weston, William Wang Yang and Scott (Wen-tau) Yih.  \nFinally, we would like to thank our program committee members, invited speakers, ACL workshop chairs. We are also thankful to IBM Research for sponsoring the Shared Task competition.  \nOrganizing Committee  \nSong Feng, IBM Research  \nSiva Reddy, McGill University and MILA Malihe Alikhani, University of Pittsburgh He He, New York University  \nYangfeng Ji, University of Virgin","cbCaijwh26p7XFrt","https://ap.wps.com/l/cbCaijwh26p7XFrt","pdf",7021284,3,1,141,"English","en",105,"# Preface\n## Shared Task Overview\n## Research Track and Technical System Track\n## Organizing Committee\n## Program Committee\n## Invited Speakers\n# DialDoc 2021 Shared Task: Goal-Oriented Document-grounded Dialogue Modeling\n## SeqDialN: Sequential Visual Dialog Network in Joint Visual-Linguistic Representation Space\n## A Template-guided Hybrid Pointer Network for Knowledge-based Task-oriented Dialogue Systems\n## Automatic Learning Assistant in Telugu","[{\"question\":\"What does DialDoc 2021 focus on?\",\"answer\":\"DialDoc 2021 focuses on document-grounded dialogue and conversational question answering, where system responses are based on relevant content from associated documents.\"},{\"question\":\"What is the Shared Task in DialDoc 2021?\",\"answer\":\"The Shared Task aims to build goal-oriented information-seeking conversation systems that identify the most relevant knowledge in a given document for generating responses.\"},{\"question\":\"What are the two subtasks in the Shared Task?\",\"answer\":\"The first subtask predicts the grounding span for the next agent response given the context, and the second subtask generates the agent response in natural language given the same context.\"}]","DialDoc 2021 - The 1st Workshop on Document-grounded Dialogue and Conversational Question Answering - Proceedings | PDF",1788506928,355,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"dialdoc-2021-the-1st-workshop-on-document-grounded-dialogue-and-conversational-question-answering-proceedings","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/dialdoc-2021-the-1st-workshop-on-document-grounded-dialogue-and-conversational-question-answering-proceedings/199755/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-09-05","2026-09-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What does DialDoc 2021 focus on?","Question",{"text":76,"@type":77},"DialDoc 2021 focuses on document-grounded dialogue and conversational question answering, where system responses are based on relevant content from associated documents.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is the Shared Task in DialDoc 2021?",{"text":81,"@type":77},"The Shared Task aims to build goal-oriented information-seeking conversation systems that identify the most relevant knowledge in a given document for generating responses.",{"name":83,"@type":74,"acceptedAnswer":84},"What are the two subtasks in the Shared Task?",{"text":85,"@type":77},"The first subtask predicts the grounding span for the next agent response given the context, and the second subtask generates the agent response in natural language given the same context.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]