arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.09241cs.CL
收藏

词类灵活性:一种深度语境化方法

Word class flexibility: A deep contextualized approach

University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究所);St. Michael’s Hospital(圣迈克尔医院)

Bai Li, Guillaume Thomas, Yang Xu, Frank Rudzicz

摘要:

词类灵活性是指一个词的形式在不同的语法范畴中使用的现象。语言类型学的大量工作试图描述跨语言的词类灵活性,但准确地量化这一现象并在规模上充满了困难。我们提出了一个原则性的方法来探索规律性的词类灵活性。我们的方法建立在上下文化词嵌入的最新工作基础上,以量化词类之间的语义转换(例如,Noun-to-verb,verb-to-noun),我们将这种方法应用于37种语言。我们发现,语境化的嵌入不仅捕捉人类的判断类变化的话在英语中,但也揭示了跨语言的类灵活性的共同趋势。具体来说,我们发现更大的语义变化时,灵活的词元在其占主导地位的词类,支持的观点,词类的灵活性是一个方向性的过程。我们的工作突出了在语言类型学的深度语境化模型的效用。

英文摘要:

Word class flexibility refers to the phenomenon whereby a single word form is used across different grammatical categories. Extensive work in linguistic typology has sought to characterize word class flexibility across languages, but quantifying this phenomenon accurately and at scale has been fraught with difficulties. We propose a principled methodology to explore regularity in word class flexibility. Our method builds on recent work in contextualized word embeddings to quantify semantic shift between word classes (e.g., noun-to-verb, verb-to-noun), and we apply this method to 37 languages. We find that contextualized embeddings not only capture human judgment of class variation within words in English, but also uncover shared tendencies in class flexibility across languages. Specifically, we find greater semantic variation when flexible lemmas are used in their dominant word class, supporting the view that word class flexibility is a directional process. Our work highlights the utility of deep contextualized models in linguistic typology.

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。

↑