2022 NAACL NAACL 2022

Distributional properties of political dogwhistle representations in Swedish BERT

Abstract

Abstract“Dogwhistles” are expressions intended by the speaker have two messages: a socially-unacceptable “in-group” message understood by a subset of listeners, and a benign message intended for the out-group. We take the result of a word-replacement survey of the Swedish population intended to reveal how dogwhistles are understood, and we show that the difficulty of annotating dogwhistles is reflected in the separability in the space of a sentence-transformer Swedish BERT trained on general data.

🧭 Keyword Pioneer — dogwhistle detection
🐣 Hot Topic Early Bird — sentence transformer
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio