{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/89027"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/89027","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Unsupervised grammar induction with Combinatory Categorial Grammars","abstract":"Language is a highly structured medium for communication. An idea starts in the speaker's mind (semantics) and is transformed into a well formed, intelligible, sentence via the specific syntactic rules of a language. We aim to discover the fingerprints of this process in the choice and location of words used in the final utterance. What is unclear is how much of this latent process can be discovered from the linguistic signal alone and how much requires shared non-linguistic context, knowledge, or cues. Unsupervised grammar induction is the task of analyzing strings in a language to discover the latent syntactic structure of the language without access to labeled training data. Successes in unsupervised grammar induction shed light on the amount of syntactic structure that is discoverable from raw or part-of-speech tagged text. In this thesis, we present a state-of-the-art grammar induction system based on Combinatory Categorial Grammars. Our choice of syntactic formalism enables the first labeled evaluation of an unsupervised system. This allows us to perform an in-depth analysis of the system’s linguistic strengths and weaknesses. In order to completely eliminate reliance on any supervised systems, we also examine how performance is affected when we use induced word clusters instead of gold-standard POS tags. Finally, we perform a semantic evaluation of induced grammars, providing unique insights into future directions for unsupervised grammar induction systems.","abstract_html":"Language is a highly structured medium for communication. An idea starts in the speaker's mind (semantics) and is transformed into a well formed, intelligible, sentence via the specific syntactic rules of a language. We aim to discover the fingerprints of this process in the choice and location of words used in the final utterance. What is unclear is how much of this latent process can be discovered from the linguistic signal alone and how much requires shared non-linguistic context, knowledge, or cues. Unsupervised grammar induction is the task of analyzing strings in a language to discover the latent syntactic structure of the language without access to labeled training data. Successes in unsupervised grammar induction shed light on the amount of syntactic structure that is discoverable from raw or part-of-speech tagged text. In this thesis, we present a state-of-the-art grammar induction system based on Combinatory Categorial Grammars. Our choice of syntactic formalism enables the first labeled evaluation of an unsupervised system. This allows us to perform an in-depth analysis of the system’s linguistic strengths and weaknesses. In order to completely eliminate reliance on any supervised systems, we also examine how performance is affected when we use induced word clusters instead of gold-standard POS tags. Finally, we perform a semantic evaluation of induced grammars, providing unique insights into future directions for unsupervised grammar induction systems.","abstract_has_math":false,"creators":["Bisk, Yonatan Yitzhak"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Hockenmaier, Julia","Eisner, Jason","Roth, Dan","Zhai, ChengXiang"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016-03-02T19:34:04Z","date_published":"2016-03-02T19:34:04Z","updated_at":"2026-07-22T22:26:32Z","subjects":["Combinatory Categorial Grammar (CCG)","Grammar Induction","Unsupervised Methods"],"languages":["en"],"rights":["Copyright 2015 Yonatan Bisk"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/89027","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hockenmaier, Julia","Eisner, Jason","Roth, Dan","Zhai, ChengXiang"]},{"key":"dc:creator","label":"Author","values":["Bisk, Yonatan Yitzhak"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2016-03-02T19:34:04Z","2015-11-30","2015-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Combinatory Categorial Grammar (CCG)","Grammar Induction","Unsupervised Methods"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2015 Yonatan Bisk"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/89027"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Language is a highly structured medium for communication. An idea starts in the speaker's mind (semantics) and is transformed into a well formed, intelligible, sentence via the specific syntactic rules of a language. We aim to discover the fingerprints of this process in the choice and location of words used in the final utterance. What is unclear is how much of this latent process can be discovered from the linguistic signal alone and how much requires shared non-linguistic context, knowledge, or cues. Unsupervised grammar induction is the task of analyzing strings in a language to discover the latent syntactic structure of the language without access to labeled training data. Successes in unsupervised grammar induction shed light on the amount of syntactic structure that is discoverable from raw or part-of-speech tagged text. In this thesis, we present a state-of-the-art grammar induction system based on Combinatory Categorial Grammars. Our choice of syntactic formalism enables the first labeled evaluation of an unsupervised system. This allows us to perform an in-depth analysis of the system’s linguistic strengths and weaknesses. In order to completely eliminate reliance on any supervised systems, we also examine how performance is affected when we use induced word clusters instead of gold-standard POS tags. Finally, we perform a semantic evaluation of induced grammars, providing unique insights into future directions for unsupervised grammar induction systems.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-03-02 without embargo terms","The student, Yonatan Bisk, accepted the attached license on 2015-11-30 at 14:55.","The student, Yonatan Bisk, submitted this Dissertation for approval on 2015-11-30 at 15:04.","This Dissertation was approved for publication on 2015-11-30 at 16:09.","DSpace SAF Submission Ingestion Package generated from Vireo submission #8876 on 2016-03-02 at 12:50:47","Made available in DSpace on 2016-03-02T19:34:04Z (GMT). No. of bitstreams: 2 BISK-DISSERTATION-2015.pdf: 3171379 bytes, checksum: 093d06af0f05aba504733ff6055ec8be (MD5) LICENSE.txt: 4209 bytes, checksum: d439ced4c5b7dde3083a5ae6ae247b6f (MD5) Previous issue date: 2015-11-30"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Unsupervised grammar induction with Combinatory Categorial Grammars"]}]}],"canonical_facts":{"dc:contributor":["Hockenmaier, Julia","Eisner, Jason","Roth, Dan","Zhai, ChengXiang"],"dc:creator":["Bisk, Yonatan Yitzhak"],"dc:date":["2016-03-02T19:34:04Z","2015-11-30","2015-12"],"dc:description":["Language is a highly structured medium for communication. An idea starts in the speaker's mind (semantics) and is transformed into a well formed, intelligible, sentence via the specific syntactic rules of a language. We aim to discover the fingerprints of this process in the choice and location of words used in the final utterance. What is unclear is how much of this latent process can be discovered from the linguistic signal alone and how much requires shared non-linguistic context, knowledge, or cues. Unsupervised grammar induction is the task of analyzing strings in a language to discover the latent syntactic structure of the language without access to labeled training data. Successes in unsupervised grammar induction shed light on the amount of syntactic structure that is discoverable from raw or part-of-speech tagged text. In this thesis, we present a state-of-the-art grammar induction system based on Combinatory Categorial Grammars. Our choice of syntactic formalism enables the first labeled evaluation of an unsupervised system. This allows us to perform an in-depth analysis of the system’s linguistic strengths and weaknesses. In order to completely eliminate reliance on any supervised systems, we also examine how performance is affected when we use induced word clusters instead of gold-standard POS tags. Finally, we perform a semantic evaluation of induced grammars, providing unique insights into future directions for unsupervised grammar induction systems.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-03-02 without embargo terms","The student, Yonatan Bisk, accepted the attached license on 2015-11-30 at 14:55.","The student, Yonatan Bisk, submitted this Dissertation for approval on 2015-11-30 at 15:04.","This Dissertation was approved for publication on 2015-11-30 at 16:09.","DSpace SAF Submission Ingestion Package generated from Vireo submission #8876 on 2016-03-02 at 12:50:47","Made available in DSpace on 2016-03-02T19:34:04Z (GMT). No. of bitstreams: 2 BISK-DISSERTATION-2015.pdf: 3171379 bytes, checksum: 093d06af0f05aba504733ff6055ec8be (MD5) LICENSE.txt: 4209 bytes, checksum: d439ced4c5b7dde3083a5ae6ae247b6f (MD5) Previous issue date: 2015-11-30"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/89027"],"dc:language":["en"],"dc:rights":["Copyright 2015 Yonatan Bisk"],"dc:subject":["Combinatory Categorial Grammar (CCG)","Grammar Induction","Unsupervised Methods"],"dc:title":["Unsupervised grammar induction with Combinatory Categorial Grammars"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:32Z"}