Cluster-specific Named Entity Transliteration

Existing named entity (NE) transliteration approaches often exploit a general model to transliterate NEs, regardless of their origins. As a result, both a Chinese name and a French name (assuming it is already translated into Chinese) will be translated into English using the same model, which often leads to unsatisfactory performance. In this paper we propose a cluster-specific NE transliteration framework. We group name origins into a smaller number of clusters, then train transliteration and language models for each cluster under a statistical machine translation framework. Given a source NE, we first select appropriate models by classifying it into the most likely cluster, then we transliterate this NE with the corresponding models. We also propose a phrase-based name transliteration model, which effectively combines context information for transliteration. Our experiments showed substantial improvement on the transliteration accuracy over a state-of-the-art baseline system, significantly reducing the transliteration character error rate from 50.29% to 12.84%.