2026-09-19T06:53:44Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/630672022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

Regina Barzilay and David R. Karger. Chen, Harr Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2011-05-23T18:12:11Z 2011-05-23T18:12:11Z 2011 2011 http://hdl.handle.net/1721.1/63067 725620956 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). 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. by Harr Chen. Ph.D. 184 p. eng Massachusetts Institute of Technology 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. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Learning semantic structures from in-domain documents Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="4a6ffc33-a52f-4bb6-be8c-bbe26d7038e2"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Learning semantic structures from in-domain documents</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2011</PublicationDate> <Authors> <Author> <DisplayName>Chen, Harr</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <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> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>