{"id":668421,"date":"2020-06-19T00:00:51","date_gmt":"2020-06-19T07:00:51","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&p=668421"},"modified":"2022-10-14T08:29:19","modified_gmt":"2022-10-14T15:29:19","slug":"neuronblocks-building-your-nlp-dnn-models-like-playing-lego","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/neuronblocks-building-your-nlp-dnn-models-like-playing-lego\/","title":{"rendered":"NeuronBlocks: Building Your NLP DNN Models Like Playing Lego"},"content":{"rendered":"
\n
Deep Neural Networks (DNN) have been widely employed in industry to address various Natural Language Processing (NLP) tasks. However, many engineers find it a big overhead when they have to choose from multiple frameworks, compare different types of models, and understand various optimization mechanisms. An NLP toolkit for DNN models with both generality and flexibility can greatly improve the productivity of engineers by saving their learning cost and guiding them to find optimal solutions to their tasks. In this paper, we introduce NeuronBlocks, a toolkit encapsulating a suite of neural network modules as building blocks to construct various DNN models with complex architecture. This toolkit empowers engineers to build, train, and test various NLP models through simple configuration of JSON files. The experiments on several NLP datasets such as GLUE, WikiQA and CoNLL-2003 demonstrate the effectiveness of NeuronBlocks. Code: https:\/\/github.com\/Microsoft\/NeuronBlocks Demo: https:\/\/youtu.be\/x6cOpVSZcdo<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

Deep Neural Networks (DNN) have been widely employed in industry to address various Natural Language Processing (NLP) tasks. However, many engineers find it a big overhead when they have to choose from multiple frameworks, compare different types of models, and understand various optimization mechanisms. An NLP toolkit for DNN models with both generality and flexibility […]<\/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":[13561,13556],"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-668421","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_publishername":"EMNLP 2019","msr_edition":"","msr_affiliation":"","msr_published_date":"2019-11-3","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":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/06\/nb-emnlp.pdf","id":"668424","title":"nb-emnlp","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/www.aclweb.org\/anthology\/D19-3028.pdf","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":668424,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/06\/nb-emnlp.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Ming Gong (YIMING)","user_id":39078,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ming Gong (YIMING)"},{"type":"user_nicename","value":"Linjun Shou (\u5bff\u6797\u94a7)","user_id":39060,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Linjun Shou (\u5bff\u6797\u94a7)"},{"type":"text","value":"Wutao Lin","user_id":0,"rest_url":false},{"type":"text","value":"Zhijie Sang","user_id":0,"rest_url":false},{"type":"text","value":"Quanjia Yan","user_id":0,"rest_url":false},{"type":"text","value":"Ze Yang","user_id":0,"rest_url":false},{"type":"text","value":"Feixiang Cheng","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Daxin Jiang (\u59dc\u5927\u6615)","user_id":31642,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Daxin Jiang (\u59dc\u5927\u6615)"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[773560],"msr_project":[651834,663420],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":651834,"post_title":"NeuronBlocks - Building Your NLP DNN Models Like Playing Lego","post_name":"neuronblocks-building-your-nlp-dnn-models-like-playing-lego","post_type":"msr-project","post_date":"2020-04-21 20:02:42","post_modified":"2020-04-24 04:14:45","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/neuronblocks-building-your-nlp-dnn-models-like-playing-lego\/","post_excerpt":"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 Gong, Linjun Shou, Wutao Lin, Zhijie Sang, Quanjia Yan, Ze Yang, Feixiang Cheng, Daxin Jiang:\u00a0 NeuronBlocks: Building Your NLP DNN…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/651834"}]}},{"ID":663420,"post_title":"Universal Question Answering in 100+ Languages","post_name":"universal-question-answering-in-100-languages","post_type":"msr-project","post_date":"2020-06-18 23:02:38","post_modified":"2020-10-02 19:48:58","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/universal-question-answering-in-100-languages\/","post_excerpt":"Provide universal Question Answering experiment to hundreds of millions of users in 100+ languages, 200+ markets\/ regions, using cuttting edge cross lingual deep learning technologies.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/663420"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/668421"}],"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":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/668421\/revisions"}],"predecessor-version":[{"id":668427,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/668421\/revisions\/668427"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=668421"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=668421"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=668421"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=668421"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=668421"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=668421"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=668421"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=668421"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=668421"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=668421"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=668421"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=668421"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=668421"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=668421"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=668421"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=668421"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}