Phrase-Based statistical machine translation for a low-density language pair

Authors:
Maxim Roy;Fred Popowich
Affiliations:
School of Computing Science, Simon Fraser University, Burnaby, BC, Canada;School of Computing Science, Simon Fraser University, Burnaby, BC, Canada
Venue:
AI'10 Proceedings of the 23rd Canadian conference on Advances in Artificial Intelligence
Year:
2010

Citing 3
Cited 0

Statistical transliteration for english-arabic cross language information retrieval

CIKM '03 Proceedings of the twelfth international conference on Information and knowledge management
Empirical methods for compound splitting

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
Moses: open source toolkit for statistical machine translation

ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a phrase-based statistical machine translation (SMT) system for Bangla to English that incorporates a novel transliteration module, and a specialized component for handling prepositions and Bangla compound words We evaluate our components through their impact on the BLEU score for the phrase-based SMT system According to the experimental results, the transliteration component has the most significant impact on the BLEU score We also provide a new test set with multiple references between Bangla and English for MT evaluation purposes Finally we propose a new manual evaluation approach for the MT community and evaluate our components using the new manual evaluation approach.