Transliteration in Any Language with Surrogate Languages

We introduce a method for transliteration generation that can produce transliterations in every language. Where previous results are only as multilingual as Wikipedia, we show how to use training data from Wikipedia as surrogate training for any language. Thus, the problem becomes one of ranking Wik...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2016-09
Main Authors: Mayhew, Stephen, Christodoulopoulos, Christos, Roth, Dan
Format: Article
Language:English
Subjects:
Languages
Ranking
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce a method for transliteration generation that can produce transliterations in every language. Where previous results are only as multilingual as Wikipedia, we show how to use training data from Wikipedia as surrogate training for any language. Thus, the problem becomes one of ranking Wikipedia languages in order of suitability with respect to a target language. We introduce several task-specific methods for ranking languages, and show that our approach is comparable to the oracle ceiling, and even outperforms it in some cases.
ISSN:2331-8422