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

CCG contextual labels in hierarchical phrase-based SMT

Almaghout, Hala and Jiang, Jie and Way, Andy (2011) CCG contextual labels in hierarchical phrase-based SMT. In: The 15th Annual Conference of the European Association for Machine Translation (EAMT-2011), 30-31 May 2011, Leuven, Belgium.

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
69Kb

Abstract

In this paper, we present a method to employ target-side syntactic contextual information in a Hierarchical Phrase-Based system. Our method uses Combinatory Categorial Grammar (CCG) to annotate training data with labels that represent the left and right syntactic context of target-side phrases. These labels are then used to assign labels to nonterminals in hierarchical rules. CCG-based contextual labels help to produce more grammatical translations by forcing phrases which replace nonterminals during translations to comply with the contextual constraints imposed by the labels. We present experiments which examine the performance of CCG contextual labels on Chinese–English and Arabic–English translation in the news and speech expressions domains using different data sizes and CCG-labeling settings. Our experiments show that our CCG contextual labels-based system achieved a 2.42% relative BLEU improvement over a PhraseBased baseline on Arabic–English translation and a 1% relative BLEU improvement over a Hierarchical Phrase-Based system baseline on Chinese–English translation.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Combinatory Categorial Grammar; CCG
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Next Generation Localisation (CNGL)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Published in:Proceedings of the 15th Annual Conference of the EAMT. . European Association for Machine Translation.
Publisher:European Association for Machine Translation
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:16402
Deposited On:21 Jul 2011 14:49 by Shane Harper. Last Modified 21 Jul 2011 14:49

Download statistics

Archive Staff Only: edit this record