arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.07599cs.CL
收藏

通过受控操控评估词汇语义在跨语言迁移中的作用

Assessing the Role of Lexical Semantics in Cross-lingual Transfer through Controlled Manipulations

Hebrew University of Jerusalem(耶路撒冷希伯来大学)

Roy Ilani, Taelin Karidi, Omri Abend

AI总结:

该研究通过人工操控英语句子模拟目标语言特征的方法,评估词汇语义等语言属性对跨语言迁移中语言与英语预训练表示空间对齐质量的影响,发现词汇匹配程度的影响远大于文字、词序等属性。

摘要:

尽管跨语言模型迁移在诸多场景中均有效,但人们对其生效条件的了解仍然有限。本文聚焦评估词汇语义在跨语言迁移中的作用,并将其影响与其他语言属性的影响进行对比。我们逐一考察每种语言属性,系统分析英语与目标语言之间的差异如何影响将该语言与英语预训练表示空间对齐的能力。我们通过人工操控英语句子以模拟目标语言的特定特征,并报告每种操控对表示空间对齐质量的影响来开展研究。研究表明,尽管文字系统或词序等属性对对齐质量的影响有限,但两种语言之间的词汇匹配程度(我们采用翻译熵度量来定义)会对其产生极大影响。

英文摘要:

While cross-linguistic model transfer is effective in many settings, there is still limited understanding of the conditions under which it works. In this paper, we focus on assessing the role of lexical semantics in cross-lingual transfer, as we compare its impact to that of other language properties. Examining each language property individually, we systematically analyze how differences between English and a target language influence the capacity to align the language with an English pretrained representation space. We do so by artificially manipulating the English sentences in ways that mimic specific characteristics of the target language, and reporting the effect of each manipulation on the quality of alignment with the representation space. We show that while properties such as the script or word order only have a limited impact on alignment quality, the degree of lexical matching between the two languages, which we define using a measure of translation entropy, greatly affects it.

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。

↑