Language model weight adaptation based on cross-entropy for statistical machine translation

Abstract. In this paper, we investigate the language model (LM) adaptation issue for Statis-tical Machine Translation (SMT). In order to overcome the weight bias on the LM obtained from the development data, a simple but effective method is proposed to adapt the LM for diverse test datasets by employing the cross entropy of translation hypotheses as a metric to measure the similarity between different datasets. Experimental results show that the cross entropy of a test dataset is closely correlated with the bias in estimating the language models and our adaptation strategy significantly outperforms a strong baseline