Dynamically Shaping the Reordering Search Space of Phrase-Based Statistical Machine Translation

Arianna Bisazza, Marcello Federico


Abstract
Defining the reordering search space is a crucial issue in phrase-based SMT between distant languages. In fact, the optimal trade-off between accuracy and complexity of decoding is nowadays reached by harshly limiting the input permutation space. We propose a method to dynamically shape such space and, thus, capture long-range word movements without hurting translation quality nor decoding time. The space defined by loose reordering constraints is dynamically pruned through a binary classifier that predicts whether a given input word should be translated right after another. The integration of this model into a phrase-based decoder improves a strong Arabic-English baseline already including state-of-the-art early distortion cost (Moore and Quirk, 2007) and hierarchical phrase orientation models (Galley and Manning, 2008). Significant improvements in the reordering of verbs are achieved by a system that is notably faster than the baseline, while bleu and meteor remain stable, or even increase, at a very high distortion limit.
Anthology ID:
Q13-1027
Volume:
Transactions of the Association for Computational Linguistics, Volume 1
Month:
Year:
2013
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
327–340
Language:
URL:
https://aclanthology.org/Q13-1027
DOI:
10.1162/tacl_a_00231
Bibkey:
Cite (ACL):
Arianna Bisazza and Marcello Federico. 2013. Dynamically Shaping the Reordering Search Space of Phrase-Based Statistical Machine Translation. Transactions of the Association for Computational Linguistics, 1:327–340.
Cite (Informal):
Dynamically Shaping the Reordering Search Space of Phrase-Based Statistical Machine Translation (Bisazza & Federico, TACL 2013)
Copy Citation:
PDF:
https://aclanthology.org/Q13-1027.pdf