arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.00340cs.CLcs.AI
收藏

Attention Link:一种高效的基于注意力的低资源机器翻译体系结构

Attention Link: An Efficient Attention-Based Low Resource Machine Translation Architecture

Peking University(北京大学)

Zeping Min

摘要:

Transformers在机器翻译中取得了巨大的成功,但基于transformer的NMT模型往往需要数百万双语并行语料进行训练。在本文中,我们提出了一种新的架构命名为注意力链接(AL),以帮助提高Transformer模型的性能,特别是在低训练资源。我们从理论上证明了我们的注意力链接架构在低训练资源的优势。此外,我们在IWSLT 14数据集上进行了大量的实验,包括en-de,de-en,en-fr,en-it,it-en,en-ro翻译任务,以及在CVIT PIB数据集上进行的bn-gu和gu-ta翻译任务。所有的实验结果表明,我们的注意力链接是强大的,可以导致显着的改善。此外,我们实现了37.9 BLEU得分,一个新的sota,在IWSLT 14 de-en任务,通过结合我们的注意力链接和其他先进的方法。

英文摘要:

Transformers have achieved great success in machine translation, but transformer-based NMT models often require millions of bilingual parallel corpus for training. In this paper, we propose a novel architecture named as attention link (AL) to help improve transformer models' performance, especially in low training resources. We theoretically demonstrate the superiority of our attention link architecture in low training resources. Besides, we have done a large number of experiments, including en-de, de-en, en-fr, en-it, it-en, en-ro translation tasks on the IWSLT14 dataset as well as real low resources scene on bn-gu and gu-ta translation tasks on the CVIT PIB dataset. All the experiment results show our attention link is powerful and can lead to a significant improvement. In addition, we achieve a 37.9 BLEU score, a new sota, on the IWSLT14 de-en task by combining our attention link and other advanced methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑