{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/91147"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/91147","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Neural network architectures for Prepositional Phrase attachment disambiguation","abstract":"This thesis addresses the problem of Prepositional Phrase (PP) attachment disambiguation, a key challenge in syntactic parsing. In natural language sentences, a PP may often be attached to several possible candidates. While humans can usually identify the correct candidate successfully, syntactic parsers are known to have high error rated on this kind of construction. This work explores the use of compositional models of meaning in choosing the correct attachment location. The compositional model is defined using a recursive neural network. Word vector representations are obtained from large amounts of raw text and fed into the neural network. The vectors are first forward propagated up the network in order to create a composite representation, which is used to score all possible candidates. In training, errors are back-propagated down the network such that the composition matrix is updated from the supervised data. Several possible neural architectures are designed and experimentally tested in both English and Arabic data sets. As a comparative system, we offer a learning-to-rank algorithm based on an SVM classifier which has access to a wide range of features. The performance of this system is compared to the compositional models.","abstract_html":"This thesis addresses the problem of Prepositional Phrase (PP) attachment disambiguation, a key challenge in syntactic parsing. In natural language sentences, a PP may often be attached to several possible candidates. While humans can usually identify the correct candidate successfully, syntactic parsers are known to have high error rated on this kind of construction. This work explores the use of compositional models of meaning in choosing the correct attachment location. The compositional model is defined using a recursive neural network. Word vector representations are obtained from large amounts of raw text and fed into the neural network. The vectors are first forward propagated up the network in order to create a composite representation, which is used to score all possible candidates. In training, errors are back-propagated down the network such that the composition matrix is updated from the supervised data. Several possible neural architectures are designed and experimentally tested in both English and Arabic data sets. As a comparative system, we offer a learning-to-rank algorithm based on an SVM classifier which has access to a wide range of features. The performance of this system is compared to the compositional models.","abstract_has_math":false,"creators":["Belinkov, Yonatan"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["Regina Barzilay."],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014","date_published":"2014","updated_at":"2026-07-22T22:22:10Z","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/1721.1/91147","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Regina Barzilay."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Belinkov, Yonatan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-10-22T14:12:33Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-10-22T14:12:33Z"]},{"key":"dc:date.issued","label":"Date","values":["2014"]},{"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/1721.1/91147"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: S.M. in Computer Science and Engineering, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.","This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","25","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 41-44)."]},{"key":"dc:description.abstract","label":"Abstract","values":["This thesis addresses the problem of Prepositional Phrase (PP) attachment disambiguation, a key challenge in syntactic parsing. In natural language sentences, a PP may often be attached to several possible candidates. While humans can usually identify the correct candidate successfully, syntactic parsers are known to have high error rated on this kind of construction. This work explores the use of compositional models of meaning in choosing the correct attachment location. The compositional model is defined using a recursive neural network. Word vector representations are obtained from large amounts of raw text and fed into the neural network. The vectors are first forward propagated up the network in order to create a composite representation, which is used to score all possible candidates. In training, errors are back-propagated down the network such that the composition matrix is updated from the supervised data. Several possible neural architectures are designed and experimentally tested in both English and Arabic data sets. As a comparative system, we offer a learning-to-rank algorithm based on an SVM classifier which has access to a wide range of features. The performance of this system is compared to the compositional models."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M. in Computer Science and Engineering"]},{"key":"dc:title","label":"Title","values":["Neural network architectures for Prepositional Phrase attachment disambiguation"]}]}],"canonical_facts":{"dc:contributor.advisor":["Regina Barzilay."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Belinkov, Yonatan"],"dc:date.accessioned":["2014-10-22T14:12:33Z"],"dc:date.available":["2014-10-22T14:12:33Z"],"dc:date.issued":["2014"],"dc:description":["Thesis: S.M. in Computer Science and Engineering, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.","This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","25","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 41-44)."],"dc:description.abstract":["This thesis addresses the problem of Prepositional Phrase (PP) attachment disambiguation, a key challenge in syntactic parsing. In natural language sentences, a PP may often be attached to several possible candidates. While humans can usually identify the correct candidate successfully, syntactic parsers are known to have high error rated on this kind of construction. This work explores the use of compositional models of meaning in choosing the correct attachment location. The compositional model is defined using a recursive neural network. Word vector representations are obtained from large amounts of raw text and fed into the neural network. The vectors are first forward propagated up the network in order to create a composite representation, which is used to score all possible candidates. In training, errors are back-propagated down the network such that the composition matrix is updated from the supervised data. Several possible neural architectures are designed and experimentally tested in both English and Arabic data sets. As a comparative system, we offer a learning-to-rank algorithm based on an SVM classifier which has access to a wide range of features. The performance of this system is compared to the compositional models."],"dc:description.degree":["S.M. in Computer Science and Engineering"],"dc:identifier.uri":["http://hdl.handle.net/1721.1/91147"],"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":["Neural network architectures for Prepositional Phrase attachment disambiguation"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:22:10Z"}