Measuring Lexico-Semantic Alignment in Debates with Contextualized Word Representations

Aina Garí Soler, Matthieu Labeau, Chloé Clavel


Abstract
Dialog participants sometimes align their linguistic styles, e.g., they use the same words and syntactic constructions as their interlocutors. We propose to investigate the notion of lexico-semantic alignment: to what extent do speakers convey the same meaning when they use the same words? We design measures of lexico-semantic alignment relying on contextualized word representations. We show that they reflect interesting semantic differences between the two sides of a debate and that they can assist in the task of debate’s winner prediction.
Anthology ID:
2023.sicon-1.6
Volume:
Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Kushal Chawla, Weiyan Shi
Venue:
SICon
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
50–63
Language:
URL:
https://aclanthology.org/2023.sicon-1.6
DOI:
10.18653/v1/2023.sicon-1.6
Bibkey:
Cite (ACL):
Aina Garí Soler, Matthieu Labeau, and Chloé Clavel. 2023. Measuring Lexico-Semantic Alignment in Debates with Contextualized Word Representations. In Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023), pages 50–63, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Measuring Lexico-Semantic Alignment in Debates with Contextualized Word Representations (Garí Soler et al., SICon 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.sicon-1.6.pdf
Video:
 https://preview.aclanthology.org/naacl24-info/2023.sicon-1.6.mp4