{"id":726154,"date":"2021-02-12T05:51:29","date_gmt":"2021-02-12T13:51:29","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=726154"},"modified":"2021-07-02T11:41:14","modified_gmt":"2021-07-02T18:41:14","slug":"inmt-interactive-neural-machine-translation-prediction","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/inmt-interactive-neural-machine-translation-prediction\/","title":{"rendered":"INMT: Interactive Neural Machine Translation Prediction"},"content":{"rendered":"<p>In this paper, we demonstrate an Interactive Machine Translation interface, that assists human translators with on-the-fly hints and suggestions. This makes the end-to-end translation process faster, more efficient and creates high-quality translations. We augment the OpenNMT backend with a mechanism to accept the user input and generate conditioned translations.<\/p>\n<div class=\"ms-editor-squiggler\" style=\"color: initial; font: initial; background: initial; background-blend-mode: initial; border: initial; border-radius: initial; border-collapse: initial; caption-side: initial; clear: initial; columns: initial; column-fill: initial; column-rule: initial; column-span: initial; cursor: initial; flex: initial; flex-flow: initial; float: initial; height: 0px; letter-spacing: initial; margin: initial; max-height: initial; max-width: initial; min-height: initial; min-width: initial; overflow: initial; padding: initial; text-align: initial; text-decoration: initial; text-indent: initial; text-transform: initial; vertical-align: initial; border-spacing: initial; width: initial;\"><\/div>\n<div class=\"ms-editor-squiggler\" style=\"color: initial; font: initial; background: initial; background-blend-mode: initial; border: initial; border-radius: initial; border-collapse: initial; caption-side: initial; clear: initial; columns: initial; column-fill: initial; column-rule: initial; column-span: initial; cursor: initial; flex: initial; flex-flow: initial; float: initial; height: 0px; letter-spacing: initial; margin: initial; max-height: initial; max-width: initial; min-height: initial; min-width: initial; overflow: initial; padding: initial; text-align: initial; text-decoration: initial; text-indent: initial; text-transform: initial; vertical-align: initial; border-spacing: initial; width: initial;\"><\/div>\n","protected":false},"excerpt":{"rendered":"<p>In this paper, we demonstrate an Interactive Machine Translation interface, that assists human translators with on-the-fly hints and suggestions. This makes the end-to-end translation process faster, more efficient and creates high-quality translations. We augment the OpenNMT backend with a mechanism to accept the user input and generate conditioned translations.<\/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":[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":[246691,248485,252484,252487],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-726154","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-language-technologies","msr-locale-en_us","msr-field-of-study-computer-science","msr-field-of-study-human-computer-interaction","msr-field-of-study-interactive-machine-translation","msr-field-of-study-user-input"],"msr_publishername":"Association for Computational Linguistics","msr_edition":"","msr_affiliation":"","msr_published_date":"2019-11-1","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":"doi","viewUrl":"false","id":"false","title":"10.18653\/V1\/D19-3018","label_id":"243106","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/www.aclweb.org\/anthology\/D19-3018.pdf","label_id":"243132","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/www.aclweb.org\/anthology\/D19-3018\/","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Sebastin Santy","user_id":0,"rest_url":false},{"type":"text","value":"Sandipan Dandapat","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Monojit Choudhury","user_id":32996,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Monojit Choudhury"},{"type":"user_nicename","value":"Kalika Bali","user_id":32477,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Kalika Bali"}],"msr_impact_theme":[],"msr_research_lab":[199562],"msr_event":[],"msr_group":[602169],"msr_project":[763693,622413],"publication":[],"video":[],"download":[757771],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":763693,"post_title":"Interactive Neural Machine Translation (INMT)","post_name":"interactive-neural-machine-translation-inmt","post_type":"msr-project","post_date":"2021-09-13 09:30:00","post_modified":"2023-01-17 11:03:42","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/interactive-neural-machine-translation-inmt\/","post_excerpt":"Through this interactive machine translation tool, we hope to not only provide help for human-aided translations for underserved languages but also for certain use cases for highly resourced languages where a human in the loop can help aid translation activities.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/763693"}]}},{"ID":622413,"post_title":"ELLORA: Enabling Low Resource Languages","post_name":"ellora","post_type":"msr-project","post_date":"2019-11-20 21:36:25","post_modified":"2019-11-20 22:39:49","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/ellora\/","post_excerpt":"The goal of ELLORA is to impact underserved communities through enabling language technology by creating economic opportunities, building technological skills, enhancing education and preserving local language and cultures for future generations.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/622413"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/726154"}],"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\/726154\/revisions"}],"predecessor-version":[{"id":757702,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/726154\/revisions\/757702"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=726154"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=726154"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=726154"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=726154"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=726154"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=726154"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=726154"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=726154"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=726154"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=726154"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=726154"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=726154"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=726154"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=726154"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=726154"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=726154"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}