英语与中文语境下的居高临下语言检测

Patronizing and Condescending Language Detection in English and Mandarin

AI 导读

该论文提出面向英语和中文的居高临下语言（PCL）自动检测系统，对比了静态词嵌入加卷积神经网络与微调 BERT 两种方案。微调 BERT 方案明显更优，在开发集上取得 0.528 的 F1 分数。PCL 是对弱势群体表达贬低与怜悯的有害语言，比显性仇恨言论更难识别，人类评审者也常难以判断。

正文 · 原文

View PDF HTML (experimental)

Abstract:Patronizing and condescending language (PCL) is a form of harmful language that belittles and assumes pity for vulnerable groups, reinforcing negative societal stereotypes. However, unlike overt hate speech, it is often difficult to detect, even for human judges. This paper proposes a system for the automated detection of PCL. Our first approach uses static word embeddings and a convolutional neural network for classification, while our second approach uses pre-trained BERT embeddings fine-tuned for the PCL task. Our second approach was considerably more successful, and achieved an F1 score of 0.528 over the development set.

Subjects:	Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.31808 [cs.AI]
	(or arXiv:2610.31808v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2610.31808 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xinyi Xiang [view email]
[v1] Thu, 22 Oct 2026 18:44:00 UTC (35 KB)

来源：arXiv cs.AI · arxiv.org