BriefGPT.xyz
Oct, 2022
利用上下文语义轴揭示人物表征中的差异
Discovering Differences in the Representation of People using Contextualized Semantic Axes
HTML
PDF
Li Lucy, Divya Tadimeti, David Bamman
TL;DR
本研究使用静态词向量嵌入,构建了上下文化的语义轴,以解决反义词有相邻表示的困境,并在两个人类数据集上验证了这些轴的效果:维基百科职业和过去14年中极端主义男性社区中的多平台讨论,结果显示上下文化的语义轴可以有效区分同一单词类型的不同实例。
Abstract
A common paradigm for identifying
semantic differences
across social and temporal contexts is the use of
static word embeddings
and their distances. In particular, past work has compared embeddings against "seman
→