Integrating N-best SMT outputs into a TM system
He, Yifan and Ma, Yanjun and Way, Andy and van Genabith, Josef (2010) Integrating N-best SMT outputs into a TM system. In: COLING 2010 - 23rd International Conference on Computational Linguistics, 23-27 August 2010, Beijing, China.
Full text available as:
In this paper, we propose a novel frame- work to enrich Translation Memory (TM) systems with Statistical Machine Translation (SMT) outputs using ranking. In order to offer the human translators multiple choices, instead of only using the top SMT output and top TM hit, we merge the N-best output from the SMT system and the k-best hits with highest fuzzy match scores from the TM system. The merged list is then ranked according to the prospective post-editing effort and provided to the translators to aid their work. Experiments show that our ranked output achieve 0.8747 precision at top 1 and 0.8134 precision at top 5. Our
framework facilitates a tight integration between SMT and TM, where full advantage is taken of TM while high quality
SMT output is availed of to improve the productivity of human translators.
Archive Staff Only: edit this record