Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation

Rico Sennrich


Abstract
The role of language models in SMT is to promote fluent translation output, but traditional n-gram language models are unable to capture fluency phenomena between distant words, such as some morphological agreement phenomena, subcategorisation, and syntactic collocations with string-level gaps. Syntactic language models have the potential to fill this modelling gap. We propose a language model for dependency structures that is relational rather than configurational and thus particularly suited for languages with a (relatively) free word order. It is trainable with Neural Networks, and not only improves over standard n-gram language models, but also outperforms related syntactic language models. We empirically demonstrate its effectiveness in terms of perplexity and as a feature function in string-to-tree SMT from English to German and Russian. We also show that using a syntactic evaluation metric to tune the log-linear parameters of an SMT system further increases translation quality when coupled with a syntactic language model.
Anthology ID:
Q15-1013
Volume:
Transactions of the Association for Computational Linguistics, Volume 3
Month:
Year:
2015
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
169–182
Language:
URL:
https://aclanthology.org/Q15-1013
DOI:
10.1162/tacl_a_00131
Bibkey:
Cite (ACL):
Rico Sennrich. 2015. Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation. Transactions of the Association for Computational Linguistics, 3:169–182.
Cite (Informal):
Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation (Sennrich, TACL 2015)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/Q15-1013.pdf
Video:
 https://vimeo.com/154064165
Data
WMT 2014