International Workshop on Spoken Language Translation (IWSLT) 2005

Pittsburgh, PA, USA
October 24-25, 2005

The TALP Ngram-based SMT System for IWSLT'05

Josep M. Crego, Adrià de Gispert, José B. Mariño

TALP Research Center, Universitat Politècnica de Catalunya, Barcelona, Spain

This paper provides a description of TALP-Ngram, the tuple-based statistical machine translation system developed at the TALP Research Center of the UPC (Universitat Polit`ecnica de Catalunya). Briefly, the system performs a log-linear combination of a translation model and additional feature functions. The translation model is estimated as an N-gram of bilingual units called tuples, and the feature functions include a target language model, a word penalty, and lexical features, depending on the language pair and task.
   The paper describes the participation of the system in the second international workshop on spoken language translation (IWSLT) held in Pittsburgh, October 2005. Results on Chinese-to-English and Arabic-to-English tracks using supplied data are reported.

Full Paper    Presentation

Bibliographic reference.  Crego, Josep M. / Gispert, Adrià de / Mariño, José B. (2005): "The TALP ngram-based SMT system for IWSLT'05", In IWSLT-2005, 181-188.