2026-09-18T18:40:42Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/533152022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Regina Barzilay.
Dzunic, Zoran, Ph. D. Massachusetts Institute of Technology
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2010-03-25T15:30:16Z
2010-03-25T15:30:16Z
2009
2009
http://hdl.handle.net/1721.1/53315
550546800
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2009.
Cataloged from PDF version of thesis.
Includes bibliographical references (p. 73-76).
Bag-of-words representations are used in many NLP applications, such as text classification and sentiment analysis. These representations ignore relations across different sentences in a text and disregard the underlying structure of documents. In this work, we present a method for text classification that takes into account document structure and only considers segments that contain information relevant for a classification task. In contrast to the previous work, which assumes that relevance annotation is given, we perform the relevance prediction in an unsupervised fashion. We develop a Conditional Bayesian Network model that incorporates relevance as a hidden variable of a target classifier. Relevance and label predictions are performed jointly, optimizing the relevance component for the best result of the target classifier. Our work demonstrates that incorporating structural information in document analysis yields significant performance gains over bag-of-words approaches on some NLP tasks.
by Zoran Dzunic.
S.M.
76 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.
Text structure-aware classification
Thesis
application/pdf
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="b65abf52-6d02-4d81-a0b6-6207598cbd80">
<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>Text structure-aware classification</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2009</PublicationDate>
<Authors>
<Author>
<DisplayName>Dzunic, Zoran, Ph. D. Massachusetts Institute of Technology</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>Bag-of-words representations are used in many NLP applications, such as text classification and sentiment analysis. These representations ignore relations across different sentences in a text and disregard the underlying structure of documents. In this work, we present a method for text classification that takes into account document structure and only considers segments that contain information relevant for a classification task. In contrast to the previous work, which assumes that relevance annotation is given, we perform the relevance prediction in an unsupervised fashion. We develop a Conditional Bayesian Network model that incorporates relevance as a hidden variable of a target classifier. Relevance and label predictions are performed jointly, optimizing the relevance component for the best result of the target classifier. Our work demonstrates that incorporating structural information in document analysis yields significant performance gains over bag-of-words approaches on some NLP tasks.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>