Ambiguity solution of pinyin segmentation in continuous Pinyin-to-Character conversion

Chinese Pinyin-to-character conversion is a key technology in Chinese Pinyin input system. In sentence based Pinyin-to-character conversion, segmentation of Pinyin string has important influence on performance of Pinyin-to-character conversion. There are lots of ambiguities in segmentation of Pinyin string. This paper classifies them into overlap and combinational ambiguities, and proposes disambiguation algorithms for them respectively. We then combine ambiguity resolution with several different language model to implement Pinyin-to-character conversion task, experiments show a good performance brought by proposed algorithms.