Mapping Source to Target Strings without Alignment by Analogical Learning: A Case Study with Transliteration
The 51st Annual Meeting of the Association for Computational Linguistics - Short Papers (ACL Short Papers 2013)
Sofia, Bulgaria, August 4-9, 2013
Analogical learning over strings is a holistic model that has been investigated by a few authors as a means to map forms of a source language to forms of a target language. In this study, we revisit this learning paradigm and apply it to the transliteration task. We show that alone, it performs worse than a statistical phrase-based machine translation engine, but the combination of both approaches outperforms each one taken separately, demonstrating the usefulness of the information captured by a so-called formal analogy.
Conference Manager (V2.61.0 - Rev. 2792M)