{"id":751528,"date":"2021-06-07T00:19:44","date_gmt":"2021-06-07T07:19:44","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=751528"},"modified":"2023-03-02T01:46:15","modified_gmt":"2023-03-02T09:46:15","slug":"retrack","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/retrack\/","title":{"rendered":"Modular and Efficient KBQA"},"content":{"rendered":"<p>Here we introduce <strong>ReTraCk<\/strong> (Retriever-Transducer-Checker), a neural semantic parsing framework for large scale knowledge base question answering (KBQA). ReTraCk is designed as a modular framework to achieve high flexibility and efficiency. The system includes a retriever to access relevant KB items efficiently, a transducer to generate logical form with syntax correctness guarantees, and a checker to improve the transduction procedure.<\/p>\n<p>ReTraCk is ranked at top1 overall performance on the <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/dki-lab.github.io\/GrailQA\/\">GrailQA leaderboard<\/a> (as of Apr\/2021) and obtains highly competitive performance on the classic <a href=\"https:\/\/www.microsoft.com\/en-us\/download\/details.aspx?id=52763\">WebQuestions Semantic Parse<\/a> benchmark. Users can interact with the system in a timely interactive manner, further demonstrating the efficiency of the proposed framework.<\/p>\n<p>Source code and Data for a system demo at ACL 2021 are <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/aka.ms\/ReTraCk\">available on GitHub.<\/a> Contributions and collaboration are very welcome!<\/p>\n<p>The Knowledge Computing group is also looking for strong research and engineering intern candidates. If you&#8217;re interested, please <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/12\/kc_intern_job_description_2020.pdf\">check our group page<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Neural semantic parsing framework for modular and efficient large scale knowledge base question answering (KBQA). Source code and Data for a system demo at ACL 2021 are available on GitHub. Contributions and collaboration are very welcome!<\/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":""},"research-area":[13556,13545,13555],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-751528","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-research-area-search-information-retrieval","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2020-12-01","related-publications":[895557],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Zhiwei Yu","user_id":39937,"people_section":"Section name 0","alias":"zhiwyu"},{"type":"user_nicename","display_name":"Chin-Yew Lin","user_id":31493,"people_section":"Section name 0","alias":"cyl"}],"msr_research_lab":[199560],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/751528"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":9,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/751528\/revisions"}],"predecessor-version":[{"id":924306,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/751528\/revisions\/924306"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=751528"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=751528"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=751528"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=751528"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=751528"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}