{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/63067"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/63067","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Learning semantic structures from in-domain documents","abstract":"Semantic analysis is a core area of natural language understanding that has typically focused on predicting domain-independent representations. However, such representations are unable to fully realize the rich diversity of technical content prevalent in a variety of specialized domains. Taking the standard supervised approach to domainspecific semantic analysis requires expensive annotation effort for each new domain of interest. In this thesis, we study how multiple granularities of semantic analysis can be learned from unlabeled documents within the same domain. By exploiting in-domain regularities in the expression of text at various layers of linguistic phenomena, including lexicography, syntax, and discourse, the statistical approaches we propose induce multiple kinds of structure: relations at the phrase and sentence level, content models at the paragraph and section level, and semantic properties at the document level. Each of our models is formulated in a hierarchical Bayesian framework with the target structure captured as latent variables, allowing them to seamlessly incorporate linguistically-motivated prior and posterior constraints, as well as multiple kinds of observations. Our empirical results demonstrate that the proposed approaches can successfully extract hidden semantic structure over a variety of domains, outperforming multiple competitive baselines.","abstract_html":"Semantic analysis is a core area of natural language understanding that has typically focused on predicting domain-independent representations. However, such representations are unable to fully realize the rich diversity of technical content prevalent in a variety of specialized domains. Taking the standard supervised approach to domainspecific semantic analysis requires expensive annotation effort for each new domain of interest. In this thesis, we study how multiple granularities of semantic analysis can be learned from unlabeled documents within the same domain. By exploiting in-domain regularities in the expression of text at various layers of linguistic phenomena, including lexicography, syntax, and discourse, the statistical approaches we propose induce multiple kinds of structure: relations at the phrase and sentence level, content models at the paragraph and section level, and semantic properties at the document level. Each of our models is formulated in a hierarchical Bayesian framework with the target structure captured as latent variables, allowing them to seamlessly incorporate linguistically-motivated prior and posterior constraints, as well as multiple kinds of observations. Our empirical results demonstrate that the proposed approaches can successfully extract hidden semantic structure over a variety of domains, outperforming multiple competitive baselines.","abstract_has_math":false,"creators":["Chen, Harr"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["Regina Barzilay and David R. Karger."],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011","date_published":"2011","updated_at":"2026-07-22T22:21:16Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/63067","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Regina Barzilay and David R. Karger."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Chen, Harr"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2011-05-23T18:12:11Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2011-05-23T18:12:11Z"]},{"key":"dc:date.issued","label":"Date","values":["2011"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/63067"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011.","Cataloged from PDF version of thesis.","Includes bibliographical references (p. 175-184)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Semantic analysis is a core area of natural language understanding that has typically focused on predicting domain-independent representations. However, such representations are unable to fully realize the rich diversity of technical content prevalent in a variety of specialized domains. Taking the standard supervised approach to domainspecific semantic analysis requires expensive annotation effort for each new domain of interest. In this thesis, we study how multiple granularities of semantic analysis can be learned from unlabeled documents within the same domain. By exploiting in-domain regularities in the expression of text at various layers of linguistic phenomena, including lexicography, syntax, and discourse, the statistical approaches we propose induce multiple kinds of structure: relations at the phrase and sentence level, content models at the paragraph and section level, and semantic properties at the document level. Each of our models is formulated in a hierarchical Bayesian framework with the target structure captured as latent variables, allowing them to seamlessly incorporate linguistically-motivated prior and posterior constraints, as well as multiple kinds of observations. Our empirical results demonstrate that the proposed approaches can successfully extract hidden semantic structure over a variety of domains, outperforming multiple competitive baselines."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Learning semantic structures from in-domain documents"]}]}],"canonical_facts":{"dc:contributor.advisor":["Regina Barzilay and David R. Karger."],"dc:contributor.department":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:creator":["Chen, Harr"],"dc:date.accessioned":["2011-05-23T18:12:11Z"],"dc:date.available":["2011-05-23T18:12:11Z"],"dc:date.issued":["2011"],"dc:description":["Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011.","Cataloged from PDF version of thesis.","Includes bibliographical references (p. 175-184)."],"dc:description.abstract":["Semantic analysis is a core area of natural language understanding that has typically focused on predicting domain-independent representations. However, such representations are unable to fully realize the rich diversity of technical content prevalent in a variety of specialized domains. Taking the standard supervised approach to domainspecific semantic analysis requires expensive annotation effort for each new domain of interest. In this thesis, we study how multiple granularities of semantic analysis can be learned from unlabeled documents within the same domain. By exploiting in-domain regularities in the expression of text at various layers of linguistic phenomena, including lexicography, syntax, and discourse, the statistical approaches we propose induce multiple kinds of structure: relations at the phrase and sentence level, content models at the paragraph and section level, and semantic properties at the document level. Each of our models is formulated in a hierarchical Bayesian framework with the target structure captured as latent variables, allowing them to seamlessly incorporate linguistically-motivated prior and posterior constraints, as well as multiple kinds of observations. Our empirical results demonstrate that the proposed approaches can successfully extract hidden semantic structure over a variety of domains, outperforming multiple competitive baselines."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/63067"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Learning semantic structures from in-domain documents"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:16Z"}