Chinese-English Backward Transliteration Assisted with Mining Monolingual Web Pages

In this paper, we present a novel backward transliteration approach which can further assist the existing statistical model by mining monolingual web resources. Firstly, we employ the syllable-based search to revise the transliteration candidates from the statistical model. By mapping all of them into existing words, we can filter or correct some pseudo candidates and improve the overall recall. Secondly, an AdaBoost model is used to rerank the revised candidates based on the information extracted from monolingual web pages. To get a better precision during the reranking process, a variety of web-based information is exploited to adjust the ranking score, so that some candidates which are less possible to be transliteration names will be assigned with lower ranks. The experimental results show that the proposed framework can significantly outperform the baseline transliteration system in both precision and recall.