2026-09-18T19:51:07Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/824122022-01-13T07:54:01Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Regina Barzilay. Lei, Tao, Ph. D. Massachusetts Institute of Technology Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2013-11-18T19:19:52Z 2013-11-18T19:19:52Z 2013 2013 http://hdl.handle.net/1721.1/82412 862113579 Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013. Cataloged from PDF version of thesis. Includes bibliographical references (p. 54-60). This thesis addresses the language grounding problem at the level of word relation extraction. We propose methods to acquire knowledge represented in the form of relations and utilize them in two domain applications, high-level planning in a complex virtual world and input parser generation from input format specifications. In the first application, we propose a reinforcement learning framework to jointly learn to predict precondition relations from text and to perform high-level planning guided by those relations. When applied to a complex virtual world and text describing that world, our relation extraction technique performs on par with a supervised baseline, and we show that a high-level planner utilizing these extracted relations significantly outperforms a strong, text unaware baseline. In the second application, we use a sampling framework to predict relation trees and to generate input parser code from those trees. Our results show that our approach outperforms a state-of-the-art semantic parser on a dataset of input format specifications from the ACM International Collegiate Programming Contest, which were written in English for humans with no intention of providing support for automated processing. by Tao Lei. S.M. 60 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. Domain knowledge acquisition via language grounding Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="c9356192-7654-4fdd-9dbd-ee41b199747d"> <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>Domain knowledge acquisition via language grounding</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2013</PublicationDate> <Authors> <Author> <DisplayName>Lei, Tao, 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>This thesis addresses the language grounding problem at the level of word relation extraction. We propose methods to acquire knowledge represented in the form of relations and utilize them in two domain applications, high-level planning in a complex virtual world and input parser generation from input format specifications. In the first application, we propose a reinforcement learning framework to jointly learn to predict precondition relations from text and to perform high-level planning guided by those relations. When applied to a complex virtual world and text describing that world, our relation extraction technique performs on par with a supervised baseline, and we show that a high-level planner utilizing these extracted relations significantly outperforms a strong, text unaware baseline. In the second application, we use a sampling framework to predict relation trees and to generate input parser code from those trees. Our results show that our approach outperforms a state-of-the-art semantic parser on a dataset of input format specifications from the ACM International Collegiate Programming Contest, which were written in English for humans with no intention of providing support for automated processing.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>