{"id":167555,"date":"2014-08-01T00:00:00","date_gmt":"2014-08-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/automatic-discovery-of-adposition-typology\/"},"modified":"2018-10-16T21:58:31","modified_gmt":"2018-10-17T04:58:31","slug":"automatic-discovery-of-adposition-typology","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/automatic-discovery-of-adposition-typology\/","title":{"rendered":"Automatic Discovery of Adposition Typology"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Natural languages (NL) can be classified as prepositional or postpositional based on the order of the noun phrase and the adposition. Categorizing a language by its adposition typology helps in addressing several challenges in linguistics and natural language processing (NLP). Understanding the adposition typologies for less-studied languages by manual analysis of large text corpora can be quite expensive, yet automatic discovery of the same has received very little attention till date. This research presents a simple unsupervised technique to automatically predict the adposition typology for a language. Most of the function words of a language are adpositions, and we show that function words can be effectively separated from content words by leveraging differences in their distributional properties in a corpus. Using this principle, we show that languages can be classified as prepositional or postpositional based on the rank correlations derived from entropies of word co-occurrence distributions. Our claims are substantiated through experiments on 23 languages from ten diverse families, 19 of which are correctly classified by our technique.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Natural languages (NL) can be classified as prepositional or postpositional based on the order of the noun phrase and the adposition. Categorizing a language by its adposition typology helps in addressing several challenges in linguistics and natural language processing (NLP). Understanding the adposition typologies for less-studied languages by manual analysis of large text corpora can [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"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-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-167555","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"Coling 2014","msr_edition":"Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers","msr_affiliation":"","msr_published_date":"2014-08-07","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"1037-1046","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":"http:\/\/www.aclweb.org\/anthology\/C\/C14\/C14-1098.pdf","msr_doi":"","msr_publication_uploader":[{"type":"url","title":"http:\/\/www.aclweb.org\/anthology\/C\/C14\/C14-1098.pdf","viewUrl":false,"id":false,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":0,"url":"http:\/\/www.aclweb.org\/anthology\/C\/C14\/C14-1098.pdf"}],"msr-author-ordering":[{"type":"text","value":"Rishiraj Saha Roy","user_id":0,"rest_url":false},{"type":"text","value":"Rahul Katare","user_id":0,"rest_url":false},{"type":"text","value":"Niloy Ganguly","user_id":0,"rest_url":false},{"type":"user_nicename","value":"monojitc","user_id":32996,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=monojitc"}],"msr_impact_theme":[],"msr_research_lab":[199562],"msr_event":[],"msr_group":[144733,144940],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/167555"}],"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\/167555\/revisions"}],"predecessor-version":[{"id":540793,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/167555\/revisions\/540793"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=167555"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=167555"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=167555"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=167555"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=167555"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=167555"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=167555"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=167555"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=167555"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=167555"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=167555"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=167555"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=167555"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=167555"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=167555"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}