Improving low-resource machine transliteration by using 3-way transfer learning

Chun Kai Wu, Chao Chuang Shih, Yu Chun Wang, Richard Tzong Han Tsai

研究成果: 雜誌貢獻期刊論文同行評審

摘要

Transfer learning brings improvement to machine translation by using a resource-rich language pair to pretrain the model and then adapting it to the desired language pair. However, to date, there have been few attempts to tackle machine transliteration with transfer learning. In this article, we propose a method of using source–pivot and pivot–target datasets to improve source–target machine transliteration. Our approach first bridges the source–pivot and pivot–target datasets by reducing the distance between source and pivot embeddings. Then, our model learns to translate from the pivot language to the target language. Finally, the source–target dataset is used to fine tune the model. Our experiments show that our method is superior to the transfer learning method. When implemented with a state-of-the-art source–target translation model from NEWS’18, our transfer learning method can improve the accuracy by 1.1%.

原文???core.languages.en_GB???
文章編號101283
期刊Computer Speech and Language
72
DOIs
出版狀態已出版 - 3月 2022

指紋

深入研究「Improving low-resource machine transliteration by using 3-way transfer learning」主題。共同形成了獨特的指紋。

引用此