One Word, Two Sides: Traces of Stance in Contextualized Word Representations

Aina Garí Soler (1) , Matthieu Labeau (2, 3, 4) , Chloé Clavel (2, 3, 4)

1 LTCI - Laboratoire Traitement et Communication de l'Information
2 IP Paris - Institut Polytechnique de Paris
3 IDS - Département Images, Données, Signal
4 S2A - Signal, Statistique et Apprentissage

The way we use words is influenced by our opinion. We investigate whether this is reflected in contextualized word embeddings. For example, is the representation of "animal" different between people who would abolish zoos and those who would not? We explore this question from a Lexical Semantic Change standpoint. Our experiments with BERT embeddings derived from datasets with stance annotations reveal small but significant differences in word representations between opposing stances.

Domaines: Informatique et langage [cs.CL]

Aina Garí Soler, Matthieu Labeau, Chloé Clavel. One Word, Two Sides: Traces of Stance in Contextualized Word Representations. 29th International Conference on Computational Linguistics (COLING 2022), Oct 2022, Gyeongju, South Korea. ⟨hal-03860830⟩