Integrating an Unsupervised Transliteration Model into Statistical Machine Translation
2014pp. 148–153
Citations Over TimeTop 1% of 2014 papers
Abstract
We investigate three methods for integrating an unsupervised transliteration model into an end-to-end SMT system. We induce a transliteration model from parallel data and use it to translate OOV words. Our approach is fully unsupervised and language independent. In the methods to integrate transliterations, we observed improvements from 0.23-0.75 ( 0.41) BLEU points across 7 language pairs. We also show that our mined transliteration corpora provide better rule coverage and translation quality compared to the gold standard transliteration corpora.
Related Papers
- → English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor(2017)2 cited
- → Recurrent Stacking of Layers for Compact Neural Machine Translation Models(2018)2 cited
- → Note on Transliteration and Translation(2002)
- → Note on Transliteration and Translation(2022)
- → A Note on Transliteration, Translation, and Sourcing(2020)