Paper: Learning Phoneme Mappings for Transliteration without Parallel Data

ACL ID N09-1005
Title Learning Phoneme Mappings for Transliteration without Parallel Data
Venue Human Language Technologies
Session Main Conference
Year 2009
Authors

We present a method for performing machine transliteration without any parallel resources. We frame the transliteration task as a deci- pherment problem and show that it is possi- ble to learn cross-language phoneme mapping tables using only monolingual resources. We compare various methods and evaluate their accuracies on a standard name transliteration task.