基于词典注入的藏汉机器翻译模型预训练方法(Dictionary Injection Based Pretraining Method for Tibetan-Chinese Machine Translation Model)

Duanzhu Sangjie (桑杰端珠), Jia Cairang (才让加)


Abstract
“近年来,预训练方法在自然语言处理领域引起了广泛关注,但是在比如藏汉机器等低资源的任务设定下,由于双语监督信息无法直接参与预训练,限制了预训练模型在此类任务上的性能改进。考虑到双语词典是丰富且廉价的先验翻译知识来源,同时受到跨语言交流中人们往往会使用混合语言增加以沟通效率这一现象启发,本文提出一种基于词典注入的藏汉机器翻译模型的预训练方法,为预训练提供学习双语知识关联的广泛可能。经验证,该方法在藏汉和汉藏翻译方向测试集上的 BLEU 值比 BART 强基准分别高出 2.3 和 2.1,证实了本文所提出的方法在藏汉机器翻译任务上的有效性。”
Anthology ID:
2022.ccl-1.34
Volume:
Proceedings of the 21st Chinese National Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Nanchang, China
Editors:
Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
374–383
Language:
Chinese
URL:
https://aclanthology.org/2022.ccl-1.34
DOI:
Bibkey:
Cite (ACL):
Duanzhu Sangjie and Jia Cairang. 2022. 基于词典注入的藏汉机器翻译模型预训练方法(Dictionary Injection Based Pretraining Method for Tibetan-Chinese Machine Translation Model). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 374–383, Nanchang, China. Chinese Information Processing Society of China.
Cite (Informal):
基于词典注入的藏汉机器翻译模型预训练方法(Dictionary Injection Based Pretraining Method for Tibetan-Chinese Machine Translation Model) (Sangjie & Cairang, CCL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2022.ccl-1.34.pdf