Resumptive Pronoun Detection for Modern Standard Arabic to English MT

Abstract

Many languages, including Modern Standard Arabic (MSA), insert resumptive pronouns in relative clauses, whereas many others, such as English, do not, using empty categories instead. This discrepancy is a source of difficulty when translating between these languages because there are words in one language that correspond to empty categories in the other, and these words must either be inserted or deleted-depending on translation direction. In this paper, we first examine challenges presented by resumptive pronouns in MSA-English translations and review resumptive pronoun translations generated by a popular online MSA-English MT engine. We then present what is, to the best of our knowledge, the first system for automatic identification of resumptive pronouns. The system achieves 91.9 F1 and 77.8 F1 on Arabic Treebank data when using gold standard parses and automatic parses, respectively.

Arabic and English Relative Clauses and Machine Translation Challenges

“…It should be noted that, a single study in Arabic MT was devoted to relative clauses despite the remarkable nature of the structure. The study was conducted by Tratz et al (2014) and its focus was limited to the challenges related to presumptive pronouns in Arabic relative clauses when translated into English. The current study, however, provides a fine-grained error analysis that includes all accuracy and fluency issues in the Arabic MT of English relative clauses and the English MT of Arabic relative clauses.…”