We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments. ConvLab offers a set of fully annotated datasets and associated pre-trained reference models. As a showcase, we extend the MultiWOZ dataset with user dialog act annotations to train all component models and demonstrate how ConvLab makes it easy and effortless to conduct complicated experiments in multi-domain end-to-end dialog settings.<\/p>\n","protected":false},"excerpt":{"rendered":"
We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments. ConvLab offers a set of fully annotated datasets and associated pre-trained reference models. As […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13545],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-579838","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2019-7-28","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2019\/04\/ACL_2019__ConvLab__Multi_Domain_End_to_end_Dialog_System_Platform.pdf","id":"579841","title":"_acl_2019__convlab__multi_domain_end_to_end_dialog_system_platform","label_id":"243132","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/1904.08637","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":579841,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2019\/04\/ACL_2019__ConvLab__Multi_Domain_End_to_end_Dialog_System_Platform.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Sungjin Lee","user_id":36377,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sungjin Lee"},{"type":"text","value":"Qi Zhu","user_id":0,"rest_url":false},{"type":"text","value":"Ryuichi Takanobu","user_id":0,"rest_url":false},{"type":"text","value":"Xiang Li","user_id":0,"rest_url":false},{"type":"text","value":"Yaoqin Zhang","user_id":0,"rest_url":false},{"type":"text","value":"Zheng Zhang","user_id":0,"rest_url":false},{"type":"text","value":"Jinchao Li","user_id":0,"rest_url":false},{"type":"text","value":"Baolin Peng","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Xiujun Li","user_id":36287,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Xiujun Li"},{"type":"text","value":"Minlie Huang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Jianfeng Gao","user_id":32246,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jianfeng Gao"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[390593],"msr_project":[645171,569514],"publication":[],"video":[],"download":[600435],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":645171,"post_title":"Multi-Domain Task-Completion Dialog Challenge II","post_name":"multi-domain-task-completion-dialog-challenge-ii","post_type":"msr-project","post_date":"2020-03-25 11:19:40","post_modified":"2020-06-12 16:21:23","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/multi-domain-task-completion-dialog-challenge-ii\/","post_excerpt":"As part of the Ninth Dialog System Technology Challenge (DSTC9), \u00a0Microsoft Research and Tsinghua University are hosting Multi-domain Task-oriented Dialog Challenge II, aiming to solve two tasks in the multi-domain task completion setting. End-to-end Multi-domain Task Completion Dialog -- In recent years there has been an increasing interest in building complex task completion bots that span over multiple domains. In this task, participants will develop an end-to-end dialog system that receives natural language as…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/645171"}]}},{"ID":569514,"post_title":"Multi-Domain Task-Completion Dialog Challenge","post_name":"multi-domain-task-completion-dialog-challenge","post_type":"msr-project","post_date":"2019-02-24 10:44:56","post_modified":"2019-06-17 13:49:02","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/multi-domain-task-completion-dialog-challenge\/","post_excerpt":"As part of the Eighth Dialog System Technology Challenge (DSTC8), Microsoft Research and Tsinghua University are hosting a track intended to foster progress in two important aspects of dialog systems: dialog complexity and scaling to new domains. For this DSTC8 track, there are two tasks you can compete in (see below). The challenge runs from\u00a0June 17, 2019 - October 6, 2019. Task 1 -\u00a0 There is increasing interest in building complex bots that span…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/569514"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/579838","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/579838\/revisions"}],"predecessor-version":[{"id":579844,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/579838\/revisions\/579844"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=579838"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=579838"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=579838"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=579838"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=579838"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=579838"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=579838"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=579838"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=579838"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=579838"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=579838"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=579838"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=579838"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=579838"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=579838"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=579838"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}