Confusion Network Based System Combination for Chinese Translation Output: Word-Level or Character-Level?
Maoxi Li, Mingwen Wang · International Conference on Computational Linguistics · 2012
Recently, confusion network based system combination has applied successfully to various machine translation tasks. However, to construct the confusion network when combining the Chinese translation outputs from multiple machine translation systems, it is possible to either take a Chinese word as the atomic unit (word-level) or take a Chinese character as the atomic unit (character-level). In this paper, we compare word-level approach with character-level approach for combining Chinese translation outputs on the NIST'08 EC tasks and IWSLT'08 EC CRR challenge tasks. Our experimental results reveal that character-level combination system significantly outperforms word-level combination system.