Phonology-Augmented Statistical Framework for Machine Transliteration using Limited Linguistic Resources
This addresses the issue of producing phonologically invalid transliterations in languages like Vietnamese and Cantonese, especially when linguistic resources are limited, though it appears incremental as it builds on statistical methods.
The paper tackles the problem of machine transliteration by proposing a phonology-augmented statistical framework that explicitly models target language phonology to avoid invalid outputs, showing it outperforms a baseline by up to 44.68% relative with limited training data (587 entries).
Transliteration converts words in a source language (e.g., English) into words in a target language (e.g., Vietnamese). This conversion considers the phonological structure of the target language, as the transliterated output needs to be pronounceable in the target language. For example, a word in Vietnamese that begins with a consonant cluster is phonologically invalid and thus would be an incorrect output of a transliteration system. Most statistical transliteration approaches, albeit being widely adopted, do not explicitly model the target language's phonology, which often results in invalid outputs. The problem is compounded by the limited linguistic resources available when converting foreign words to transliterated words in the target language. In this work, we present a phonology-augmented statistical framework suitable for transliteration, especially when only limited linguistic resources are available. We propose the concept of pseudo-syllables as structures representing how segments of a foreign word are organized according to the syllables of the target language's phonology. We performed transliteration experiments on Vietnamese and Cantonese. We show that the proposed framework outperforms the statistical baseline by up to 44.68% relative, when there are limited training examples (587 entries).