arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.07348cs.CLcs.LG
收藏

单语模型的跨语言迁移

Cross-lingual Transfer of Monolingual Models

RISE Research Institutes of Sweden(瑞典RISE研究院);AI Sweden(瑞典AI)

Evangelia Gogoulou, Ariel Ekgren, Tim Isbister, Magnus Sahlgren

摘要:

最近使用多语言模型进行zero-shot跨语言学习的研究已经否定了以前的假设,即共享词汇和联合预训练是跨语言泛化的关键。受此启发,我们提出了一种基于领域自适应的单语模型跨语言迁移方法。我们研究了从四种不同的语言到英语的这种迁移的效果。我们在GLUE上的实验结果表明,迁移模型的性能优于母语英语模型,与源语言无关。通过对迁移前后表征中的英语语言知识的分析,我们发现语义信息在迁移过程中从源语言中保留下来,而句法信息在迁移过程中习得。此外,在源语言任务中对迁移模型的评估结果表明,迁移后它们在源域中的表现恶化。

英文摘要:

Recent studies in zero-shot cross-lingual learning using multilingual models have falsified the previous hypothesis that shared vocabulary and joint pre-training are the keys to cross-lingual generalization. Inspired by this advancement, we introduce a cross-lingual transfer method for monolingual models based on domain adaptation. We study the effects of such transfer from four different languages to English. Our experimental results on GLUE show that the transferred models outperform the native English model independently of the source language. After probing the English linguistic knowledge encoded in the representations before and after transfer, we find that semantic information is retained from the source language, while syntactic information is learned during transfer. Additionally, the results of evaluating the transferred models in source language tasks reveal that their performance in the source domain deteriorates after transfer.

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。

↑