Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/78356
Title: Source language adaptation for resource-poor machine translation
Authors: Wang, P.
Nakov, P.
Ng, H.T. 
Issue Date: 2012
Source: Wang, P.,Nakov, P.,Ng, H.T. (2012). Source language adaptation for resource-poor machine translation. EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference : 286-296. ScholarBank@NUS Repository.
Abstract: We propose a novel, language-independent approach for improving machine translation from a resource-poor language to X by adapting a large bi-text for a related resource-rich language and X (the same target language). We assume a small bi-text for the resource-poor language to X pair, which we use to learn word-level and phrase-level paraphrases and cross-lingual morphological variants between the resource-rich and the resource-poor language; we then adapt the former to get closer to the latter. Our experiments for Indonesian/Malay-English translation show that using the large adapted resource-rich bi-text yields 6.7 BLEU points of improvement over the unadapted one and 2.6 BLEU points over the original small bi-text. Moreover, combining the small bi-text with the adapted bi-text outperforms the corresponding combinations with the unadapted bi-text by 1.5-3 BLEU points. We also demonstrate applicability to other languages and domains. © 2012 Association for Computational Linguistics.
Source Title: EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference
URI: http://scholarbank.nus.edu.sg/handle/10635/78356
ISBN: 9781937284435
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

22
checked on Feb 17, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.