The TALP ngram-based SMT system for IWSLT 2007

Patrik Lambert, Marta R. Costa-jussà, Josep M. Crego, Maxim Khalilov, José B. Mariño, Rafael E. Banchs, José A. R. Fonollosa, Holger Schwenk


Abstract
This paper describes TALPtuples, the 2007 N-gram-based statistical machine translation system developed at the TALP Research Center of the UPC (Universitat Polite`cnica de Catalunya) in Barcelona. Emphasis is put on improvements and extensions of the system of previous years. Mainly, these include optimizing alignment parameters in function of translation metric scores and rescoring with a neural network language model. Results on two translation directions are reported, namely from Arabic and Chinese into English, thoroughly explaining all language-related preprocessing and translation schemes.
Anthology ID:
2007.iwslt-1.26
Volume:
Proceedings of the Fourth International Workshop on Spoken Language Translation
Month:
October 15-16
Year:
2007
Address:
Trento, Italy
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
Language:
URL:
https://aclanthology.org/2007.iwslt-1.26
DOI:
Bibkey:
Cite (ACL):
Patrik Lambert, Marta R. Costa-jussà, Josep M. Crego, Maxim Khalilov, José B. Mariño, Rafael E. Banchs, José A. R. Fonollosa, and Holger Schwenk. 2007. The TALP ngram-based SMT system for IWSLT 2007. In Proceedings of the Fourth International Workshop on Spoken Language Translation, Trento, Italy.
Cite (Informal):
The TALP ngram-based SMT system for IWSLT 2007 (Lambert et al., IWSLT 2007)
Copy Citation:
PDF:
https://aclanthology.org/2007.iwslt-1.26.pdf