Bidirectional segmentation for English-Korean machine translation

Unlike English or Spanish, which has each word clearly segmented, morphologically rich languages, such as Korean, do not have clear optimal word boundaries for machine translation (MT). Previous work has shown that segmenting such languages by incorporating information available from parallel corpus can improve MT results. In this thesis we show that this can be improved further by segmenting both source and target languages and present improvement in BLEU scores from 3.13 to 3.46 for English-Korean translation.