2026-09-20T01:12:20Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/461652022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Michael Collins. Katz-Brown, Jason Edward Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2009-06-30T17:34:43Z 2009-06-30T17:34:43Z 2008 2008 http://hdl.handle.net/1721.1/46165 399964893 Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008. Includes bibliographical references (p. 101-106). Translating Japanese into English is very challenging because of the vast difference in word order between the two languages. For example, the main verb is always at the very end of a Japanese sentence, whereas it comes near the beginning of an English sentence. In this thesis, we develop a Japanese-to-English translation system capable of performing the long-distance reordering necessary to fluently translate Japanese into English. Our system uses novel feature functions, based on a dependency parse of the input Japanese sentence, which identify candidate translations that put dependency relationships into correct English order. For example, one feature identifies translations that put verbs before their objects. The weights for these feature functions are discriminatively trained, and so can be used for any language pair. In our Japanese-to-English system, they improve the BLEU score from 27.96 to 28.54, and we show clear improvements in subjective quality. We also experiment with a well-known technique of training the translation system on a Japanese training corpus that has been reordered into an English-like word order. Impressive results can be achieved by naively reordering each Japanese sentence into reverse order. Translating these reversed sentences with the dependency-parse-based feature functions gives further improvement. Finally, we evaluate our translation systems with human judgment, BLEU score, and METEOR score. We compare these metrics on corpus and sentence level and examine how well they capture improvements in translation word order. by Jason Edward Katz-Brown. M.Eng. 106 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. Dependency reordering features for Japanese-English phrase-based translation Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="e43b7953-b63f-4d55-93ae-02681f2ee5e0"> <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>Dependency reordering features for Japanese-English phrase-based translation</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2008</PublicationDate> <Authors> <Author> <DisplayName>Katz-Brown, Jason Edward</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>Translating Japanese into English is very challenging because of the vast difference in word order between the two languages. For example, the main verb is always at the very end of a Japanese sentence, whereas it comes near the beginning of an English sentence. In this thesis, we develop a Japanese-to-English translation system capable of performing the long-distance reordering necessary to fluently translate Japanese into English. Our system uses novel feature functions, based on a dependency parse of the input Japanese sentence, which identify candidate translations that put dependency relationships into correct English order. For example, one feature identifies translations that put verbs before their objects. The weights for these feature functions are discriminatively trained, and so can be used for any language pair. In our Japanese-to-English system, they improve the BLEU score from 27.96 to 28.54, and we show clear improvements in subjective quality. We also experiment with a well-known technique of training the translation system on a Japanese training corpus that has been reordered into an English-like word order. Impressive results can be achieved by naively reordering each Japanese sentence into reverse order. Translating these reversed sentences with the dependency-parse-based feature functions gives further improvement. Finally, we evaluate our translation systems with human judgment, BLEU score, and METEOR score. We compare these metrics on corpus and sentence level and examine how well they capture improvements in translation word order.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>