Lexicalized Reordering for Left-to-Right Hierarchical Phrase-based Translation

Maryam Siahbani, Anoop Sarkar


Abstract
Phrase-based and hierarchical phrase-based (Hiero) translation models differ radically in the way reordering is modeled. Lexicalized reordering models play an important role in phrase-based MT and such models have been added to CKY-based decoders for Hiero. Watanabe et al. (2006) proposed a promising decoding algorithm for Hiero (LR-Hiero) that visits input spans in arbitrary order and produces the translation in left to right (LR) order which leads to far fewer language model calls and leads to a considerable speedup in decoding. We introduce a novel shift-reduce algorithm to LR-Hiero to decode with our lexicalized reordering model (LRM) and show that it improves translation quality for Czech-English, Chinese-English and German-English.
Anthology ID:
E17-2097
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
612–618
Language:
URL:
https://aclanthology.org/E17-2097
DOI:
Bibkey:
Cite (ACL):
Maryam Siahbani and Anoop Sarkar. 2017. Lexicalized Reordering for Left-to-Right Hierarchical Phrase-based Translation. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 612–618, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Lexicalized Reordering for Left-to-Right Hierarchical Phrase-based Translation (Siahbani & Sarkar, EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-2097.pdf