{"id":651834,"date":"2020-04-21T20:02:42","date_gmt":"2020-04-22T03:02:42","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=651834"},"modified":"2020-04-24T04:14:45","modified_gmt":"2020-04-24T11:14:45","slug":"neuronblocks-building-your-nlp-dnn-models-like-playing-lego","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/neuronblocks-building-your-nlp-dnn-models-like-playing-lego\/","title":{"rendered":"NeuronBlocks &#8211; Building Your NLP DNN Models Like Playing Lego"},"content":{"rendered":"<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-651873\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/neuronblocks-logo-300x38.png\" alt=\"\" width=\"300\" height=\"38\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/neuronblocks-logo-300x38.png 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/neuronblocks-logo-1024x131.png 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/neuronblocks-logo-768x98.png 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/neuronblocks-logo-1536x197.png 1536w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/neuronblocks-logo-2048x262.png 2048w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<h2>Building Your NLP DNN Models Like Playing Lego.<\/h2>\n<p>NeuronBlocks is a\u00a0<strong>NLP deep learning modeling toolkit<\/strong>\u00a0that helps engineers\/researchers to build end-to-end pipelines for neural network model training for NLP tasks. The main goal of this toolkit is to minimize developing cost for NLP deep neural network model building, including both training and inference stages.<\/p>\n<ul>\n<li><strong>Paper<\/strong>: Ming Gong, Linjun Shou, Wutao Lin, Zhijie Sang, Quanjia Yan, Ze Yang, Feixiang Cheng, Daxin Jiang:\u00a0 <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/www.aclweb.org\/anthology\/D19-3028\/\">NeuronBlocks: Building Your NLP DNN Models Like Playing<span class=\"sr-only\"> (opens in new tab)<\/span><\/a> Lego.\u00a0EMNLP, 2019.<\/li>\n<li><strong>Github<\/strong>:\u00a0 <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/github.com\/microsoft\/NeuronBlocks\"><span class=\"tagnamecolor\"><span class=\"tagcolor\">https:\/\/github.com\/microsoft\/NeuronBlocks<\/span><\/span><span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/li>\n<li><strong>Demo video<\/strong>: <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/www.youtube.com\/watch?v=x6cOpVSZcdo\"><span class=\"tagnamecolor\"><span class=\"attributecolor\"><span class=\"attributevaluecolor\">https:\/\/www.youtube.com\/watch?v=x6cOpVSZcdo<\/span><\/span><\/span><span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/li>\n<\/ul>\n<p>NeuronBlocks consists of two major components:\u00a0<em><strong>Block Zoo<\/strong><\/em>\u00a0and\u00a0<em><strong>Model Zoo<\/strong><\/em>.<\/p>\n<ul>\n<li>In\u00a0<em><strong>Block Zoo<\/strong><\/em>, we provide commonly used neural network components as building blocks for model architecture design.<\/li>\n<li>In\u00a0<em><strong>Model Zoo<\/strong><\/em>, we provide a suite of NLP models for common NLP tasks, in the form of\u00a0<strong>JSON configuration<\/strong>\u00a0files.<\/li>\n<\/ul>\n<p><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/camo.githubusercontent.com\/1b32b8c260d4d59292060a193f962f2c870993e7\/68747470733a2f2f692e696d6775722e636f6d2f4c4d44305046512e706e67\" target=\"_blank\" rel=\"noopener noreferrer\"><img decoding=\"async\" src=\"https:\/\/camo.githubusercontent.com\/1b32b8c260d4d59292060a193f962f2c870993e7\/68747470733a2f2f692e696d6775722e636f6d2f4c4d44305046512e706e67\" width=\"250\" data-canonical-src=\"https:\/\/i.imgur.com\/LMD0PFQ.png\" \/><span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Building Your NLP DNN Models Like Playing Lego. NeuronBlocks is a\u00a0NLP deep learning modeling toolkit\u00a0that helps engineers\/researchers to build end-to-end pipelines for neural network model training for NLP tasks. The main goal of this toolkit is to minimize developing cost for NLP deep neural network model building, including both training and inference stages. Paper: Ming [&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":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-651834","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2020-03-01","related-publications":[668421],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Ming Gong (YIMING)","user_id":39078,"people_section":"Section name 0","alias":"migon"},{"type":"user_nicename","display_name":"Linjun Shou (\u5bff\u6797\u94a7)","user_id":39060,"people_section":"Section name 0","alias":"lisho"},{"type":"guest","display_name":"Wutao  Lin","user_id":651864,"people_section":"Section name 0","alias":""},{"type":"guest","display_name":"Zhijie Sang","user_id":651882,"people_section":"Section name 0","alias":""},{"type":"guest","display_name":"Feixiang Cheng","user_id":651885,"people_section":"Section name 0","alias":""}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/651834"}],"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":4,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/651834\/revisions"}],"predecessor-version":[{"id":652476,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/651834\/revisions\/652476"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=651834"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=651834"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=651834"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=651834"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=651834"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}