Lexical translation model using a deep neural network architecture

Thanh-Le Ha, Jan Niehues, Alex Waibel


Abstract
In this paper we combine the advantages of a model using global source sentence contexts, the Discriminative Word Lexicon, and neural networks. By using deep neural networks instead of the linear maximum entropy model in the Discriminative Word Lexicon models, we are able to leverage dependencies between different source words due to the non-linearity. Furthermore, the models for different target words can share parameters and therefore data sparsity problems are effectively reduced. By using this approach in a state-of-the-art translation system, we can improve the performance by up to 0.5 BLEU points for three different language pairs on the TED translation task.
Anthology ID:
2014.iwslt-papers.10
Volume:
Proceedings of the 11th International Workshop on Spoken Language Translation: Papers
Month:
December 4-5
Year:
2014
Address:
Lake Tahoe, California
Editors:
Marcello Federico, Sebastian Stüker, François Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
223–229
Language:
URL:
https://aclanthology.org/2014.iwslt-papers.10
DOI:
Bibkey:
Cite (ACL):
Thanh-Le Ha, Jan Niehues, and Alex Waibel. 2014. Lexical translation model using a deep neural network architecture. In Proceedings of the 11th International Workshop on Spoken Language Translation: Papers, pages 223–229, Lake Tahoe, California.
Cite (Informal):
Lexical translation model using a deep neural network architecture (Ha et al., IWSLT 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.iwslt-papers.10.pdf