Suppr超能文献

词嵌入的理论基础与局限性:它们能捕捉哪些类型的意义?

Theoretical foundations and limits of word embeddings: What types of meaning can they capture?

作者信息

Arseniev-Koehler Alina

机构信息

Department of Sociology, Purdue University.

Division of Biomedical Informatics, University of California, San Diego.

出版信息

Sociol Methods Res. 2024 Nov;53(4):1753-1793. doi: 10.1177/00491241221140142. Epub 2022 Dec 7.

Abstract

Measuring meaning is a central problem in cultural sociology and word embeddings may offer powerful new tools to do so. But like any tool, they build on and exert theoretical assumptions. In this paper I theorize the ways in which word embeddings model three core premises of a structural linguistic theory of meaning: that meaning is coherent, relational, and may be analyzed as a static system. In certain ways, word embeddings are vulnerable to the enduring critiques of these premises. In other ways, word embeddings offer novel solutions to these critiques. More broadly, formalizing the study of meaning with word embeddings offers theoretical opportunities to clarify core concepts and debates in cultural sociology, such as the coherence of meaning. Just as network analysis specified the once vague notion of social relations, formalizing meaning with embeddings can push us to specify and reimagine meaning itself.

摘要

衡量意义是文化社会学中的一个核心问题,而词嵌入可能为此提供强大的新工具。但与任何工具一样,它们基于并运用理论假设。在本文中,我将从理论上探讨词嵌入对意义的结构语言学理论的三个核心前提进行建模的方式:意义是连贯的、关系性的,并且可以作为一个静态系统进行分析。在某些方面,词嵌入容易受到对这些前提的持久批判。在其他方面,词嵌入为这些批判提供了新颖的解决方案。更广泛地说,用词嵌入将意义研究形式化,为澄清文化社会学中的核心概念和辩论(如意义的连贯性)提供了理论机会。正如网络分析明确了曾经模糊的社会关系概念一样,用词嵌入将意义形式化可以促使我们明确并重新构想意义本身。

相似文献

2
Improved biomedical word embeddings in the transformer era.Transformer 时代改进的生物医学词向量。
J Biomed Inform. 2021 Aug;120:103867. doi: 10.1016/j.jbi.2021.103867. Epub 2021 Jul 18.
3
Using word embeddings to investigate cultural biases.利用词嵌入来研究文化偏见。
Br J Soc Psychol. 2023 Jan;62(1):617-629. doi: 10.1111/bjso.12560. Epub 2022 Jul 23.

本文引用的文献

4
Integrating topic modeling and word embedding to characterize violent deaths.整合主题建模和词嵌入技术以刻画暴力死亡事件
Proc Natl Acad Sci U S A. 2022 Mar 8;119(10):e2108801119. doi: 10.1073/pnas.2108801119. Epub 2022 Mar 3.
5
What Might Books Be Teaching Young Children About Gender?儿童书籍在教给孩子什么是性别?
Psychol Sci. 2022 Jan;33(1):33-47. doi: 10.1177/09567976211024643. Epub 2021 Dec 23.
6
Building semantic memory from embodied and distributional language experience.从具身和分布语言经验中构建语义记忆。
Wiley Interdiscip Rev Cogn Sci. 2021 Sep;12(5):e1555. doi: 10.1002/wcs.1555. Epub 2021 Feb 2.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验