Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora

Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation estimates and low coverage over source and target phrases. This paper presents a method which alleviates this problem by exploiting multiple translations of the same source phrase. Central to our approach is triangulation, the process of translating from a source to a target language via an intermediate third language. This allows the use of a much wider range of parallel corpora for training, and can be combined with a standard phrase-table using conventional smoothing methods. Experimental results demonstrate BLEU improvements for triangulated models over a standard phrase-based system.

• Type: Conference
• Year: 2007
• Where: ACL
• Authors: Trevor Cohn, Mirella Lapata
• Keywords: ACL 2007, Computational Linguistics, Current Phrase-based Smt, Standard Phrase-based System, Unreliable Translation Estimates