{"id":629865,"date":"2019-12-03T00:00:07","date_gmt":"2019-12-03T08:00:07","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=629865"},"modified":"2020-01-07T12:49:30","modified_gmt":"2020-01-07T20:49:30","slug":"conversations-based-on-search-engine-result-pages","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/conversations-based-on-search-engine-result-pages\/","title":{"rendered":"Conversations Based on Search Engine Result Pages"},"content":{"rendered":"<p>How might we convey the information that is traditionally returned by a search engine in the form of a complex search engine result page (SERP) in a meaningful and natural conversation? In the talk, Maarten starts from recent work on so-called background based conversations, where a conversational agent has access to additional background information to help it generate more natural and appropriate responses. Then, he talks about ongoing work on our next step: SERP-based conversations. He explains the task definitions, describes pipelines (subtasks), baselines, datasets, etc. Finally, Maarten describes the differences between background-based and SERP-based conversations and their relations to other, related tasks. Work on SERP-based conversations is in its early stages, leaving lots of opportunities for follow-up research.<\/p>\n<p>Based on joint work with Zhumin Chen, Jun Ma, Chuan Meng, Christof Monz, Pengjie Ren, Svitlana Vakulenko, and Nikos Voskarides.<\/p>\n<p><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2020\/01\/44612_compressed.pdf\" rel=\"noopener noreferrer\" target=\"_blank\">[Talk slides]<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>How might we convey the information that is traditionally returned by a search engine in the form of a complex search engine result page (SERP) in a meaningful and natural conversation? In the talk, Maarten starts from recent work on so-called background based conversations, where a conversational agent has access to additional background information to [&hellip;]<\/p>\n","protected":false},"featured_media":629874,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_hide_image_in_river":0,"footnotes":""},"research-area":[13556,13555],"msr-video-type":[242367],"msr-locale":[268875],"msr-post-option":[],"msr-session-type":[],"msr-impact-theme":[],"msr-pillar":[],"msr-episode":[],"msr-research-theme":[],"class_list":["post-629865","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-research-area-search-information-retrieval","msr-video-type-ai-distinguished-lecture-series","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/oMWeNR0fQpc","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/629865","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/629865\/revisions"}],"predecessor-version":[{"id":629880,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/629865\/revisions\/629880"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/629874"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=629865"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=629865"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=629865"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=629865"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=629865"},{"taxonomy":"msr-session-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-session-type?post=629865"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=629865"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=629865"},{"taxonomy":"msr-episode","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-episode?post=629865"},{"taxonomy":"msr-research-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-theme?post=629865"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}