Language Model Adaptation in Machine Translation from Speech
Ivan Bulyko, Spyros Matsoukas, Richard M. Schwartz, Long Tuan Nguyen, John I. Makhoul · 2007
This paper investigates the use of several language model adaptation techniques applied to the task of machine translation from Arabic broadcast speech. Unsupervised and discriminative approaches slightly outperform the traditional perplexity-based optimization technique. Language model adaptation, when used for n-best rescoring, improves machine translation performance by 0.3-0.4 BLEU and reduces translation edit rate (TER) by 0.2-0.5% compared to an unadapted LM.