Morphology to the rescue redux: Resolving borrowings and code-mixing in machine translation

Abstract

In the IBM LMT machine translation system, derivational morphological rules recognize and analyze words that are not found in its source lexicons, and generate default transfers for these unlisted words. Unfound words with no inflectional or derivational affixes are by default nouns. These rules are now expanded to provide lexical coverage of a particular set of words created on the fly in emails by bilingual Spanish-English speakers. What characterizes the approach is the generation of additional default parts of speech, and the use of morphological, semantic, and syntactic features from both source and target lexicons for analysis and transfer. A built-in rule-based strategy to handle language borrowing and code-mixing allows for the recognition of words with variable and unpredictable frequency of occurrence, which would remain otherwise unfound, thus affecting the accuracy of parsing and the quality of translation output. © 2011 Springer-Verlag.