Knowledge bases (KBs) are often greatly incomplete, necessitating a demand for KB completion. The path ranking algorithm (PRA) is one of the most promising approaches to this task. Previous work on PRA usually follows a single-task learning paradigm, building a prediction model for each relation independently with its own training data. It ignores meaningful associations among certain relations, and might not get enough training data for less frequent relations. This paper proposes a novel multi-task learning framework for PRA, referred to as coupled PRA (CPRA). It first devises an agglomerative clustering strategy to automatically discover relations that are highly correlated to each other, and then employs a multi-task learning strategy to effectively couple the prediction of such relations. As such, CPRA takes into account relation association and enables implicit data sharing among them. We empirically evaluate CPRA on benchmark data created from Freebase. Experimental results show that CPRA can effectively identify coherent clusters in which relations are highly correlated. By further coupling such relations, CPRA significantly outperforms PRA, in terms of both predictive accuracy and model interpretability<\/p>\n","protected":false},"excerpt":{"rendered":"
Knowledge bases (KBs) are often greatly incomplete, necessitating a demand for KB completion. The path ranking algorithm (PRA) is one of the most promising approaches to this task. Previous work on PRA usually follows a single-task learning paradigm, building a prediction model for each relation independently with its own training data. It ignores meaningful associations […]<\/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-294959","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":"ACL - Association for Computational Linguistics","msr_edition":"","msr_affiliation":"","msr_published_date":"2016-8-7","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":"294971","msr_publicationurl":"http:\/\/www.aclweb.org\/anthology\/P\/P16\/P16-1124.pdf","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/09\/2016-acl-p1308.pdf","id":"294971","title":"2016-acl-p1308","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"http:\/\/www.aclweb.org\/anthology\/P\/P16\/P16-1124.pdf","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":0,"url":"http:\/\/www.aclweb.org\/anthology\/P\/P16\/P16-1124.pdf"}],"msr-author-ordering":[{"type":"text","value":"Quan Wang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Jing Liu","user_id":32706,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jing Liu"},{"type":"text","value":"Yuanfei Luo","user_id":0,"rest_url":false},{"type":"text","value":"Bin Wang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Chin-Yew Lin","user_id":31493,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Chin-Yew Lin"}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[144919],"msr_project":[714646],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":714646,"post_title":"VERT: Versatile Entity Recognition & Disambiguation Toolkit","post_name":"vert-versatile-entity-recognition-disambiguation-toolkit","post_type":"msr-project","post_date":"2020-12-30 02:54:35","post_modified":"2021-10-13 21:15:01","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/vert-versatile-entity-recognition-disambiguation-toolkit\/","post_excerpt":"While knowledge about entities is a key building block in the mentioned systems, creating effective\/efficient models for real-world scenarios remains a challenge (tech\/data\/real workloads). Based on such needs, we've created VERT - a Versatile Entity Recognition & Disambiguation Toolkit. VERT is a pragmatic toolkit that combines rules and ML, offering both powerful pretrained models for core entity types (recognition and linking) and the easy creation of custom models. Custom models use our deep learning-based NER\/EL…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/714646"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/294959"}],"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":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/294959\/revisions"}],"predecessor-version":[{"id":537898,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/294959\/revisions\/537898"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=294959"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=294959"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=294959"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=294959"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=294959"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=294959"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=294959"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=294959"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=294959"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=294959"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=294959"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=294959"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=294959"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=294959"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=294959"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=294959"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}