Abstract

We propose new methods to take advantage of text in resource-rich languages to sharpen statistical language models in resource-deficient languages. We achieve this through an extension of the method of lexical triggers to the cross-language problem, and by developing a likelihoodbased adaptation scheme for combining a trigger model with an-gram model. We describe the application of such language models for automatic speech recognition. By exploiting a side-corpus of contemporaneous English news articles for adapting a static Chinese language model to transcribe Mandarin news stories, we demonstrate significant reductions in both perplexity and recognition errors. We also compare our cross-lingual adaptation scheme to monolingual language model adaptation, and to an alternate method for exploiting cross-lingual cues, via crosslingual information retrieval and machine translation, proposed elsewhere. 1 Data Sparseness in Language Modeling Statistical techniques have been remarkably successful in automatic speech recognition (ASR) and natural language processing (NLP) over the last two decades. This success, however, depends crucially

Citations