A Neural Verb Lexicon Model with Source-side Syntactic Context for String-to-Tree Machine Translation

Maria Nădejde, Alexandra Birch, Philipp Koehn


Abstract
String-to-tree MT systems translate verbs without lexical or syntactic context on the source side and with limited target-side context. The lack of context is one reason why verb translation recall is as low as 45.5%. We propose a verb lexicon model trained with a feed-forward neural network that predicts the target verb conditioned on a wide source-side context. We show that a syntactic context extracted from the dependency parse of the source sentence improves the model’s accuracy by 1.5% over a baseline trained on a window context. When used as an extra feature for re-ranking the n-best list produced by the string-to-tree MT system, the verb lexicon model improves verb translation recall by more than 7%.
Anthology ID:
2016.iwslt-1.11
Volume:
Proceedings of the 13th International Conference on Spoken Language Translation
Month:
December 8-9
Year:
2016
Address:
Seattle, Washington D.C
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
International Workshop on Spoken Language Translation
Note:
Pages:
Language:
URL:
https://aclanthology.org/2016.iwslt-1.11
DOI:
Bibkey:
Cite (ACL):
Maria Nădejde, Alexandra Birch, and Philipp Koehn. 2016. A Neural Verb Lexicon Model with Source-side Syntactic Context for String-to-Tree Machine Translation. In Proceedings of the 13th International Conference on Spoken Language Translation, Seattle, Washington D.C. International Workshop on Spoken Language Translation.
Cite (Informal):
A Neural Verb Lexicon Model with Source-side Syntactic Context for String-to-Tree Machine Translation (Nădejde et al., IWSLT 2016)
Copy Citation:
PDF:
https://aclanthology.org/2016.iwslt-1.11.pdf