Abstract

This paper proposes a method to harvest regional transliteration variants with guided search. We first study how to incorporate transliteration knowledge into query formulation so as to significantly increase the chance of desired transliteration returns. Then, we study a cross-training algorithm, which explores valuable information across different regional corpora for the learning of transliteration models to in turn improve the overall extraction performance. The experimental results show that the proposed method not only effectively harvests a lexicon of regional transliteration variants but also mitigates the need of manual data labeling for transliteration modeling. We also conduct an inquiry into the underlying characteristics of regional transliterations that motivate the cross-training algorithm.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.