publication . Contribution for newspaper or weekly magazine . Conference object . 2007

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

Trevor Cohn; Lapata, M.;
Open Access English
  • Published: 01 Jan 2007
  • Country: United Kingdom
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 tri...
Related Organizations
Download fromView all 1 versions
Open Access
Edinburgh Research Explorer
Contribution for newspaper or weekly magazine . 2007
Any information missing or wrong?Report an Issue