{"id":162643,"date":"2012-07-01T00:00:00","date_gmt":"2012-07-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/computational-approaches-to-sentence-completion\/"},"modified":"2018-10-16T20:38:19","modified_gmt":"2018-10-17T03:38:19","slug":"computational-approaches-to-sentence-completion","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/computational-approaches-to-sentence-completion\/","title":{"rendered":"Computational Approaches to Sentence Completion"},"content":{"rendered":"<div class=\"asset-content\">\n<p>This paper studies the problem of sentence level semantic coherence by answering SATstyle sentence completion questions. These questions test the ability of algorithms to distinguish sense from nonsense based on a variety of sentence-level phenomena. We tackle the problem with two approaches: methods that use local lexical information, such as the n-grams of a classical language model; and methods that evaluate global coherence, such as latent semantic analysis. We evaluate these methods on a suite of practice SAT questions, and on a recently released sentence completion task based on data taken from five Conan Doyle novels. We find that by fusing local and global information, we can exceed 50% on this task, and we suggest some avenues for further research.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>This paper studies the problem of sentence level semantic coherence by answering SATstyle sentence completion questions. These questions test the ability of algorithms to distinguish sense from nonsense based on a variety of sentence-level phenomena. We tackle the problem with two approaches: methods that use local lexical information, such as the n-grams of a classical [&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":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[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-162643","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_publishername":"ACL\/SIGPARSE","msr_edition":"ACL 2012","msr_affiliation":"","msr_published_date":"2012-07-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"ACL 2012","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":"205929","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"semco.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/semco.pdf","id":205929,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":205929,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/semco.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"jplatt","user_id":32416,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=jplatt"},{"type":"user_nicename","value":"gzweig","user_id":31938,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=gzweig"},{"type":"user_nicename","value":"meek","user_id":32868,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=meek"},{"type":"user_nicename","value":"cburges","user_id":31351,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=cburges"},{"type":"user_nicename","value":"t-ainury","user_id":0,"rest_url":false},{"type":"text","value":"Qiang Liu","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[171065,170884],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":171065,"post_title":"Recurrent Neural Networks for Language Processing","post_name":"recurrent-neural-networks-for-language-processing","post_type":"msr-project","post_date":"2012-11-23 11:45:31","post_modified":"2019-08-19 14:55:37","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/recurrent-neural-networks-for-language-processing\/","post_excerpt":"This project focuses on advancing the state-of-the-art in language processing with recurrent neural networks. We are currently applying these to language modeling, machine translation, speech recognition, language understanding and meaning representation. A special interest in is adding side-channels of information as input, to model phenomena which are not easily handled in other frameworks. A toolkit for doing RNN language modeling with side-information is in the associated download. Sample word vectors for use with this toolkit&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171065"}]}},{"ID":170884,"post_title":"MSR Sentence Completion Challenge","post_name":"msr-sentence-completion-challenge","post_type":"msr-project","post_date":"2011-12-08 11:11:26","post_modified":"2017-05-31 16:13:49","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/msr-sentence-completion-challenge\/","post_excerpt":"The MSR sentence completion challenge is intended to stimulate research in the area of semantic modeling. The challenge set consists of fill-in-the-blank questions similar to those found on the widely used Scholastic Aptitude Test. The sentence completion questions we focus on test the students ability to select words which are meaningful and coherent in the the context of a complete sentence. In general, this determination cannot be made on the basis of grammatical correctness alone.&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/170884"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/162643","targetHints":{"allow":["GET"]}}],"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\/162643\/revisions"}],"predecessor-version":[{"id":529230,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/162643\/revisions\/529230"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=162643"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=162643"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=162643"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=162643"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=162643"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=162643"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=162643"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=162643"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=162643"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=162643"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=162643"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=162643"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=162643"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=162643"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=162643"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=162643"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}