arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.09526cs.CLcs.LG
收藏

迭代自监督训练的跨语言检索

Cross-lingual Retrieval for Iterative Self-Supervised Training

Facebook AI(Facebook AI(脸书人工智能))

Chau Tran, Yuqing Tang, Xian Li, Jiatao Gu

摘要:

最近的研究已经证明了多语言预训练语言模型的跨语言对齐能力。在这项工作中,我们发现跨语言对齐可以通过在使用自己的编码器输出挖掘的句子对上训练seq 2seq模型来进一步改进。我们利用这些发现开发了一种新的方法-跨语言检索迭代自监督训练(CRISS),其中迭代地应用挖掘和训练过程,同时提高跨语言对齐和翻译能力。使用这种方法,我们在9种语言方向上实现了最先进的无监督机器翻译结果,平均提高了2.4 BLEU,并且在16种语言的XTREME基准测试中的Tatoeba句子检索任务中,绝对准确率平均提高了21.5%。此外,与mBART相比,CRISS在监督机器翻译下游任务上进行微调时,平均还带来了额外的1.8 BLEU改进。

英文摘要:

Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models. In this work, we found that the cross-lingual alignment can be further improved by training seq2seq models on sentence pairs mined using their own encoder outputs. We utilized these findings to develop a new approach -- cross-lingual retrieval for iterative self-supervised training (CRISS), where mining and training processes are applied iteratively, improving cross-lingual alignment and translation ability at the same time. Using this method, we achieved state-of-the-art unsupervised machine translation results on 9 language directions with an average improvement of 2.4 BLEU, and on the Tatoeba sentence retrieval task in the XTREME benchmark on 16 languages with an average improvement of 21.5% in absolute accuracy. Furthermore, CRISS also brings an additional 1.8 BLEU improvement on average compared to mBART, when finetuned on supervised machine translation downstream tasks.

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。

↑