We report on an on-going research project aimed at increasing the range of translation equivalents which can be automatically discovered by MT systems. The methodology is based on...
Performance of n-gram language models depends to a large extent on the amount of training text material available for building the models and the degree to which this text matches...
Aligned corpora are often-used resources in CLIR systems. The three qualities of translation corpora that most dramatically affect the performance of a corpus-based CLIR system are...
In Chinese texts, words composed of single or multiple characters are not separated by spaces, unlike most western languages. Therefore Chinese word segmentation is considered an ...