Discriminative adaptation of continuous space translation models

Quoc-Khanh Do, Alexandre Allauzen, François Yvon


Abstract
In this paper we explore various adaptation techniques for continuous space translation models (CSTMs). We consider the following practical situation: given a large scale, state-of-the-art SMT system containing a CSTM, the task is to adapt the CSTM to a new domain using a (relatively) small in-domain parallel corpus. Our method relies on the definition of a new discriminative loss function for the CSTM that borrows from both the max-margin and pair-wise ranking approaches. In our experiments, the baseline out-of-domain SMT system is initially trained for the WMT News translation task, and the CSTM is to be adapted to the lecture translation task as defined by IWSLT evaluation campaign. Experimental results show that an improvement of 1.5 BLEU points can be achieved with the proposed adaptation method.
Anthology ID:
2014.iwslt-papers.6
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:
192–199
Language:
URL:
https://aclanthology.org/2014.iwslt-papers.6
DOI:
Bibkey:
Cite (ACL):
Quoc-Khanh Do, Alexandre Allauzen, and François Yvon. 2014. Discriminative adaptation of continuous space translation models. In Proceedings of the 11th International Workshop on Spoken Language Translation: Papers, pages 192–199, Lake Tahoe, California.
Cite (Informal):
Discriminative adaptation of continuous space translation models (Do et al., IWSLT 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.iwslt-papers.6.pdf