arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.10397cs.CL
收藏

用于语义变化检测的语法分析

Grammatical Profiling for Semantic Change Detection

ILLC, University of Amsterdam(阿姆斯特丹大学逻辑、语言与计算研究所);University of Oslo(奥斯陆大学);University of Helsinki(赫尔辛基大学)

Mario Giulianelli, Andrey Kutuzov, Lidia Pivovarova

摘要:

语义学、词法学和句法学是相互依存的。然而,大多数用于语义变化检测的计算方法使用主要对语义进行编码的分布式词表示。我们调查的另一种方法,语法分析,完全基于单词的形态句法行为的变化。我们证明,它可以用于语义变化检测,甚至优于一些分布式语义方法。我们提出了一个深入的定性和定量分析的预测,我们的语法分析系统,表明他们是合理的和可解释的。

英文摘要:

Semantics, morphology and syntax are strongly interdependent. However, the majority of computational methods for semantic change detection use distributional word representations which encode mostly semantics. We investigate an alternative method, grammatical profiling, based entirely on changes in the morphosyntactic behaviour of words. We demonstrate that it can be used for semantic change detection and even outperforms some distributional semantic methods. We present an in-depth qualitative and quantitative analysis of the predictions made by our grammatical profiling system, showing that they are plausible and interpretable.

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。

↑