Knowledge Sources for Word-Level Translation Models

2001, English, 9 pages, .ps, .ps.gz, .pdf, .pdf.gz. Published at EMNLP 2001 at Pittsburgh, Pennsylvania.

We present various methods to train word-level translation models for statistical machine translation systems that use widely different knowledge sources ranging from parallel corpora and a bilingual lexicon to only monolingual corpora in two languages. Some novel methods are presented and previously published methods are reviewed. Also, a common evaluation metric enables the first quantitative comparison of these approaches.