2007.iwslt-1.26@ACL

#1 The TALP ngram-based SMT system for IWSLT 2007 [PDF] [Copy] [Kimi¹]

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

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.