{"id":215405,"date":"2016-04-11T00:00:00","date_gmt":"2016-04-11T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/improving-document-ranking-with-dual-word-embeddings\/"},"modified":"2024-09-04T14:03:15","modified_gmt":"2024-09-04T21:03:15","slug":"improving-document-ranking-with-dual-word-embeddings","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/improving-document-ranking-with-dual-word-embeddings\/","title":{"rendered":"Improving Document Ranking with Dual Word Embeddings"},"content":{"rendered":"<div class=\"asset-content\">\n<p>This paper investigates the popular neural word embedding method Word2vec as a source of evidence in document ranking. In contrast to NLP applications of word2vec, which tend to use only the input embeddings, we retain both the input and the output embeddings, allowing us to calculate a different word similarity that may be more suitable for document ranking. We map the query words into the input space and the document words into the output space, and compute a relevance score by aggregating the cosine similarities across all the query-document word pairs. We postulate that the proposed Dual Embedding Space Model (DESM) provides evidence that a document is about a query term, in addition to and complementing the traditional term frequency based approach.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>This paper investigates the popular neural word embedding method Word2vec as a source of evidence in document ranking. In contrast to NLP applications of word2vec, which tend to use only the input embeddings, we retain both the input and the output embeddings, allowing us to calculate a different word similarity that may be more suitable [&hellip;]<\/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":[13556,13555],"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-215405","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-search-information-retrieval","msr-locale-en_us"],"msr_publishername":"WWW - World Wide Web Consortium (W3C)","msr_edition":"","msr_affiliation":"","msr_published_date":"2016-4-11","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":"215562","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/04\/pp1291-Nalisnick.pdf","id":"215562","title":"pp1291-Nalisnick.pdf","label_id":"243109","label":0},{"type":"doi","viewUrl":"false","id":"false","title":"10.1145\/2872518.2889361","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":215562,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/04\/pp1291-Nalisnick.pdf"}],"msr-author-ordering":[{"type":"text","value":"Eric Nalisnick","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Bhaskar Mitra","user_id":31257,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Bhaskar Mitra"},{"type":"user_nicename","value":"Nick Craswell","user_id":33088,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Nick Craswell"},{"type":"user_nicename","value":"Rich Caruana","user_id":33365,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Rich Caruana"}],"msr_impact_theme":[],"msr_research_lab":[199561],"msr_event":[],"msr_group":[267093],"msr_project":[212091],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":212091,"post_title":"Dual Embedding Space Model (DESM)","post_name":"dual-embedding-space-model-desm","post_type":"msr-project","post_date":"2016-01-21 11:53:38","post_modified":"2019-08-19 10:21:11","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/dual-embedding-space-model-desm\/","post_excerpt":"The Dual Embedding Space Model (DESM) is an information retrieval model that uses two word embeddings, one for query words and one for document words. It takes into account the vector similarity between each query word vector and all document word vectors. A key challenge for information retrieval is to model document aboutness. The traditional approach uses term frequency, with more occurrences of a query word indicating that the document is more likely to be&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/212091"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/215405"}],"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":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/215405\/revisions"}],"predecessor-version":[{"id":1082604,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/215405\/revisions\/1082604"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=215405"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=215405"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=215405"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=215405"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=215405"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=215405"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=215405"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=215405"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=215405"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=215405"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=215405"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=215405"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=215405"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=215405"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=215405"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=215405"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}