Analyzing the Surprising Variability in Word Embedding Stability Across Languages
Analyzing the Surprising Variability in Word Embedding Stability Across Languages
复制标题
DOI：
10.18653/v1/2021.emnlp-main.476
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Laura Burdick;Jonathan K. Kummerfeld;Rada Mihalcea
中科院分区：
文献类型：
--
作者：
Laura Burdick;Jonathan K. Kummerfeld;Rada Mihalcea
词嵌入是一种强大的表示，它构成了许多自然语言处理体系结构的基础，无论是在英语中还是在其他语言中。为了进一步深入了解词嵌入，我们在不同的语言中探索了它们的稳定性（例如，在不同的嵌入空间中，单词的最近邻居之间的重叠）。我们讨论了与稳定性相关的语言特性，得出了与词缀、语言性别系统和其他特征相关的见解。这对嵌入使用有影响，特别是在使用它们来研究语言趋势的研究中。
Word embeddings are powerful representations that form the foundation of many natural language processing architectures, both in English and in other languages. To gain further insight into word embeddings, we explore their stability (e.g., overlap between the nearest neighbors of a word in different embedding spaces) in diverse languages. We discuss linguistic properties that are related to stability, drawing out insights about correlations with affixing, language gender systems, and other features. This has implications for embedding use, particularly in research that uses them to study language trends.