Adversarial Training for News Stance Detection: Leveraging Signals from a Multi-Genre Corpus.

Costanza Conforti, Jakob Berndt, Marco Basaldella, Mohammad Taher Pilehvar, Chryssi Giannitsarou, Flavio Toxvaerd, Nigel Collier


Abstract
Cross-target generalization constitutes an important issue for news Stance Detection (SD). In this short paper, we investigate adversarial cross-genre SD, where knowledge from annotated user-generated data is leveraged to improve news SD on targets unseen during training. We implement a BERT-based adversarial network and show experimental performance improvements over a set of strong baselines. Given the abundance of user-generated data, which are considerably less expensive to retrieve and annotate than news articles, this constitutes a promising research direction.
Anthology ID:
2021.hackashop-1.1
Volume:
Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation
Month:
April
Year:
2021
Address:
Online
Editors:
Hannu Toivonen, Michele Boggia
Venue:
Hackashop
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–7
Language:
URL:
https://aclanthology.org/2021.hackashop-1.1
DOI:
Bibkey:
Cite (ACL):
Costanza Conforti, Jakob Berndt, Marco Basaldella, Mohammad Taher Pilehvar, Chryssi Giannitsarou, Flavio Toxvaerd, and Nigel Collier. 2021. Adversarial Training for News Stance Detection: Leveraging Signals from a Multi-Genre Corpus.. In Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation, pages 1–7, Online. Association for Computational Linguistics.
Cite (Informal):
Adversarial Training for News Stance Detection: Leveraging Signals from a Multi-Genre Corpus. (Conforti et al., Hackashop 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.hackashop-1.1.pdf