Using Semantic Equivalents for Arabic-to-English Example-Based Translation

We explore the effect of using Arabic semantic equivalents in an example-based Arabic-English translation system. We describe two experiments using single-word equivalents in translation as test cases for broadening the level of similarity and using multi-word Arabic paraphrases in the future. In the first experiment, we use synonymous Arabic nouns, derived from a lexicon, to help locate potential translation examples for fragments of a given input sentence. Not surprisingly, the smaller the parallel corpus, the greater the contribution provided by synonyms. Considering the degree of relevance of the subject matter of a potential match contributes to the quality of the final results. In the second experiment, we used automatically extracted single-word verb paraphrases, derived from a corpus of comparable documents. The experiments were performed within an implementation of a nonstructural example-based translation system, using a parallel corpus aligned at the sentence level. The methods developed here should apply to other morphologically-rich languages.