Paper: Mapping Source to Target Strings without Alignment by Analogical Learning: A Case Study with Transliteration

ACL ID P13-2120
Title Mapping Source to Target Strings without Alignment by Analogical Learning: A Case Study with Transliteration
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

Analogical learning over strings is a holis- tic model that has been investigated by a few authors as a means to map forms of a source language to forms of a target lan- guage. In this study, we revisit this learn- ing paradigm and apply it to the translit- eration task. We show that alone, it per- forms worse than a statistical phrase-based machine translation engine, but the com- bination of both approaches outperforms each one taken separately, demonstrating the usefulness of the information captured by a so-called formal analogy.