Using TERp to augment the system combination for SMT
Du, JinhuaORCID: 0000-0002-3267-4881 and Way, AndyORCID: 0000-0001-5736-5930
(2010)
Using TERp to augment the system combination for SMT.
In: AMTA 2010 - 9th Conference of the Association for Machine Translation in the Americas, 31 October - 4 November 2010, Denver, CO, USA.
TER-Plus (TERp) is an extended TER evaluation metric incorporating morphology, synonymy and paraphrases.
There are three new edit operations in TERp: Stem Matches, Synonym Matches and Phrase Substitutions (Para-phrases). In this paper, we propose a TERp-based augmented system combination in terms of the backbone selection and consensus decoding network. Combining the new properties
of the TERp, we also propose a two-pass decoding strategy for the lattice-based phrase-level confusion network(CN) to generate the final result. The experiments conducted on the NIST2008 Chinese-to-English test set show that our TERp-based augmented system combination framework achieves significant improvements in terms of BLEU and TERp scores compared to the state-of-the-art word-level system combination framework and a TER-based combination strategy.