Show simple item record

dc.contributor.advisorRegina Barzilay.en_US
dc.contributor.authorDeshpande, Pawanen_US
dc.contributor.otherMassachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2008-05-19T16:05:01Z
dc.date.available2008-05-19T16:05:01Z
dc.date.copyright2007en_US
dc.date.issued2007en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/41647
dc.descriptionThesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2007.en_US
dc.descriptionIncludes bibliographical references (p. 79-85).en_US
dc.description.abstractThis thesis focuses on developing decoding techniques for complex Natural Language Processing (NLP) tasks. The goal of decoding is to find an optimal or near optimal solution given a model that defines the goodness of a candidate. The task is challenging because in a typical problem the search space is large, and the dependencies between elements of the solution are complex. The goal of this work is two-fold. First, we are interested in developing decoding techniques with strong theoretical guarantees. We develop a decoding model based on the Integer Linear Programming paradigm which is guaranteed to compute the optimal solution and is capable of accounting for a wide range of global constraints. As an alternative, we also present a novel randomized algorithm which can guarantee an arbitrarily high probability of finding the optimal solution. We apply these methods to the task of constructing temporal graphs and to the task of title generation. Second, we are interested in carefully investigating the relations between learning and decoding. We build on the Perceptron framework to integrate the learning and decoding procedures into a single unified process. We use the resulting model to automatically generate tables-of-contents, structures with deep hierarchies and rich contextual dependencies. In all three natural language tasks, our experimental results demonstrate that theoretically grounded and stronger decoding strategies perform better than existing methods. As a final contribution, we have made the source code for these algorithms publicly available for the NLP research community.en_US
dc.description.statementofresponsibilityby Pawan Deshpande.en_US
dc.format.extent85 p.en_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsM.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.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectElectrical Engineering and Computer Science.en_US
dc.titleDecoding algorithms for complex natural language tasksen_US
dc.typeThesisen_US
dc.description.degreeM.Eng.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.en_US
dc.identifier.oclc219709911en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record