arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.13309cs.CLcs.LG
收藏

多语言模型在语码转换中有效吗?

Are Multilingual Models Effective in Code-Switching?

Center for Artificial Intelligence Research (CAiRE)(人工智能研究中心(CAiRE));The Hong Kong University of Science and Technology(香港科技大学)

Genta Indra Winata, Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin, Andrea Madotto, Pascale Fung

摘要:

多语言语言模型在多语言和跨语言自然语言理解任务中表现出了良好的性能。然而,这些多语言模型在语码转换任务中的作用还没有得到充分的研究。在本文中,我们研究的多语言语言模型的有效性,了解他们的能力和适应性的混合语言设置考虑的推理速度,性能和参数的数量来衡量其实用性。我们在三种语言对上进行了命名实体识别和词性标注的实验,并将它们与现有的方法进行了比较,例如使用双语嵌入和多语言元嵌入。我们的研究结果表明,预先训练的多语言模型不一定能保证代码转换的高质量表示,而使用元嵌入可以用更少的参数实现类似的结果。

英文摘要:

Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this paper, we study the effectiveness of multilingual language models to understand their capability and adaptability to the mixed-language setting by considering the inference speed, performance, and number of parameters to measure their practicality. We conduct experiments in three language pairs on named entity recognition and part-of-speech tagging and compare them with existing methods, such as using bilingual embeddings and multilingual meta-embeddings. Our findings suggest that pre-trained multilingual models do not necessarily guarantee high-quality representations on code-switching, while using meta-embeddings achieves similar results with significantly fewer parameters.

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。

↑