A Topic-Triggered Language Model for Statistical Machine Translation

Language model is an essential part in statistical machine translation, but traditional n-gram language models can only capture a limited local context in the translated sentence, thus lacking the global information for prediction. This paper describes a novel topic-triggered language model, which takes into account the topical context by estimating the n-gram probability under the given topics and online adjusts language model score according to different topic distributions. Experimental results show that our method provides a average improvement of +0.76 Bleu on NIST Chinese-to-English translation task and a reduction in word perplexity of the test-document.