Using Wordnet to Improve Reordering in Hierarchical Phrase-Based Statistical Machine Translation

Arefeh Kazemi, Antonio Toral, Andy Way


Abstract
We propose the use of WordNet synsets in a syntax-based reordering model for hierarchical statistical machine translation (HPB-SMT) to enable the model to generalize to phrases not seen in the training data but that have equivalent meaning. We detail our methodology to incorporate synsets’ knowledge in the reordering model and evaluate the resulting WordNet-enhanced SMT systems on the English-to-Farsi language direction. The inclusion of synsets leads to the best BLEU score, outperforming the baseline (standard HPB-SMT) by 0.6 points absolute.
Anthology ID:
2016.gwc-1.24
Volume:
Proceedings of the 8th Global WordNet Conference (GWC)
Month:
27--30 January
Year:
2016
Address:
Bucharest, Romania
Editors:
Christiane Fellbaum, Piek Vossen, Verginica Barbu Mititelu, Corina Forascu
Venue:
GWC
SIG:
SIGLEX
Publisher:
Global Wordnet Association
Note:
Pages:
155–161
Language:
URL:
https://aclanthology.org/2016.gwc-1.24
DOI:
Bibkey:
Cite (ACL):
Arefeh Kazemi, Antonio Toral, and Andy Way. 2016. Using Wordnet to Improve Reordering in Hierarchical Phrase-Based Statistical Machine Translation. In Proceedings of the 8th Global WordNet Conference (GWC), pages 155–161, Bucharest, Romania. Global Wordnet Association.
Cite (Informal):
Using Wordnet to Improve Reordering in Hierarchical Phrase-Based Statistical Machine Translation (Kazemi et al., GWC 2016)
Copy Citation:
PDF:
https://aclanthology.org/2016.gwc-1.24.pdf