{"id":18902,"date":"2019-05-19T12:37:23","date_gmt":"2019-05-19T09:37:23","guid":{"rendered":"https:\/\/hgpu.org\/?p=18902"},"modified":"2019-05-19T12:37:23","modified_gmt":"2019-05-19T09:37:23","slug":"neural-query-language-a-knowledge-base-query-language-for-tensorflow","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=18902","title":{"rendered":"Neural Query Language: A Knowledge Base Query Language for Tensorflow"},"content":{"rendered":"<p>Large knowledge bases (KBs) are useful for many AI tasks, but are difficult to integrate into modern gradient-based learning systems. Here we describe a framework for accessing soft symbolic database using only differentiable operators. For example, this framework makes it easy to conveniently write neural models that adjust confidences associated with facts in a soft KB; incorporate prior knowledge in the form of hand-coded KB access rules; or learn to instantiate query templates using information extracted from text. NQL can work well with KBs with millions of tuples and hundreds of thousands of entities on a single GPU.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Large knowledge bases (KBs) are useful for many AI tasks, but are difficult to integrate into modern gradient-based learning systems. Here we describe a framework for accessing soft symbolic database using only differentiable operators. For example, this framework makes it easy to conveniently write neural models that adjust confidences associated with facts in a soft [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,3],"tags":[1782,667,1673,176,67],"class_list":["post-18902","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-paper","tag-computer-science","tag-databases","tag-deep-learning","tag-package","tag-performance"],"views":2392,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18902","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=18902"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18902\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=18902"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=18902"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=18902"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}