Abstract

The quality of Arabic-English statistical machine translation often suffers as a result of standard phrase-based SMT systems ’ inability to perform long-range re-orderings, specifically those needed to translate VSO-ordered Arabic sentences. This problem is further exacerbated by the low performance of Arabic parsers on subject and subject span detection. In this paper, we present two parse “fuzzification” techniques which allow the translation system to select among a range of possible S–V re-orderings. With this approach, we demonstrate a 0.3-point improvement in BLEU score (69 % of the maximum possible using gold parses), and a corresponding improvement in the percentage of syntactically well-formed subjects under a manual evaluation. 1

Citations