Browse DORAS
Browse Theses
Search
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

A syntactified direct translation model with linear-time decoding

Hassan, Hany and Sima'an, Khalil and Way, Andy (2009) A syntactified direct translation model with linear-time decoding. In: EMNLP 2009 - Conference on Empirical Methods in Natural Language Processing, 6-7 August 2009, Singapore.

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
190Kb

Abstract

Recent syntactic extensions of statistical translation models work with a synchronous context-free or tree-substitution grammar extracted from an automatically parsed parallel corpus. The decoders accompanying these extensions typically exceed quadratic time complexity. This paper extends the Direct Translation Model 2 (DTM2) with syntax while maintaining linear-time decoding. We employ a linear-time parsing algorithm based on an eager, incremental interpretation of Combinatory Categorial Grammar (CCG). As every input word is processed, the local parsing decisions resolve ambiguity eagerly, by selecting a single supertag–operator pair for extending the dependency parse incrementally. Alongside translation features extracted from the derived parse tree, we explore syntactic features extracted from the incremental derivation process. Our empirical experiments show that our model significantly outperforms the state-of-the art DTM2 system.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:statistical translation models;
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > National Centre for Language Technology (NCLT)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Publisher:Association for Computational Linguistics
Official URL:http://www.aclweb.org/anthology/D/D09/
Copyright Information:© 2009 ACL and AFNLP
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:15180
Deposited On:15 Feb 2010 16:33 by DORAS Administrator. Last Modified 15 Feb 2010 16:33

Download statistics

Archive Staff Only: edit this record