Mixed Embedding of XLM for Unsupervised Cantonese-Chinese Neural Machine Translation (Student Abstract)

研究成果: 書貢獻/報告類型會議論文篇章同行評審

1 引文 斯高帕斯(Scopus)

摘要

Unsupervised Neural Machines Translation is the most ideal method to apply to Cantonese and Chinese translation because parallel data is scarce in this language pair. In this paper, we proposed a method that combined a modified cross-lingual language model and performed layer to layer attention on unsupervised neural machine translation. In our experiments, we observed that our proposed method does improve the Cantonese to Chinese and Chinese to Cantonese translation by 1.088 and 0.394 BLEU scores. We finally developed a web service based on our ideal approach to provide Cantonese to Chinese Translation and vice versa.

原文???core.languages.en_GB???
主出版物標題IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations
發行者Association for the Advancement of Artificial Intelligence
頁面13081-13082
頁數2
ISBN(電子)1577358767, 9781577358763
DOIs
出版狀態已出版 - 30 6月 2022
事件36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
持續時間: 22 2月 20221 3月 2022

出版系列

名字Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
36

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???36th AAAI Conference on Artificial Intelligence, AAAI 2022
城市Virtual, Online
期間22/02/221/03/22

指紋

深入研究「Mixed Embedding of XLM for Unsupervised Cantonese-Chinese Neural Machine Translation (Student Abstract)」主題。共同形成了獨特的指紋。

引用此