This paper describes the systems submitted by FBK for the MT and SLT tracks of IWSLT 2014. We participated in the English-French and German-English machine translation tasks, as well as the English-French speech translation task. We report improvements in our English-French MT systems over last year’s baselines, largely due to improved techniques of combining translation and language models, and using huge language models. For our German-English system, we experimented with a novel domain adaptation technique. For both language pairs we also applied a novel word trigger-based model which shows slight improvements on English-French and German-English systems. Our English-French SLT system utilizes MT-based punctuation insertion, recasing, and ASR-like synthesized MT training data.
FBK’s Machine Translation and Speech Translation Systems for the IWSLT 2014 Evaluation Campaign
Bertoldi, Nicola;Mathur, Prashant;Ruiz, Nicholas;Federico, Marcello
2014-01-01
Abstract
This paper describes the systems submitted by FBK for the MT and SLT tracks of IWSLT 2014. We participated in the English-French and German-English machine translation tasks, as well as the English-French speech translation task. We report improvements in our English-French MT systems over last year’s baselines, largely due to improved techniques of combining translation and language models, and using huge language models. For our German-English system, we experimented with a novel domain adaptation technique. For both language pairs we also applied a novel word trigger-based model which shows slight improvements on English-French and German-English systems. Our English-French SLT system utilizes MT-based punctuation insertion, recasing, and ASR-like synthesized MT training data.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
