Integrating Transformers and Knowledge Graphs for Twitter Stance Detection

Thomas Clark, Costanza Conforti, Fangyu Liu, Zaiqiao Meng, Ehsan Shareghi, Nigel Collier


Abstract
Stance detection (SD) entails classifying the sentiment of a text towards a given target, and is a relevant sub-task for opinion mining and social media analysis. Recent works have explored knowledge infusion supplementing the linguistic competence and latent knowledge of large pre-trained language models with structured knowledge graphs (KGs), yet few works have applied such methods to the SD task. In this work, we first perform stance-relevant knowledge probing on Transformers-based pre-trained models in a zero-shot setting, showing these models’ latent real-world knowledge about SD targets and their sensitivity to context. We then train and evaluate new knowledge-enriched stance detection models on two Twitter stance datasets, achieving state-of-the-art performance on both.
Anthology ID:
2021.wnut-1.34
Volume:
Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
Month:
November
Year:
2021
Address:
Online
Editors:
Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
304–312
Language:
URL:
https://aclanthology.org/2021.wnut-1.34
DOI:
10.18653/v1/2021.wnut-1.34
Bibkey:
Cite (ACL):
Thomas Clark, Costanza Conforti, Fangyu Liu, Zaiqiao Meng, Ehsan Shareghi, and Nigel Collier. 2021. Integrating Transformers and Knowledge Graphs for Twitter Stance Detection. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 304–312, Online. Association for Computational Linguistics.
Cite (Informal):
Integrating Transformers and Knowledge Graphs for Twitter Stance Detection (Clark et al., WNUT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wnut-1.34.pdf
Data
LAMA