Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations

Emily Allaway, Kathleen McKeown


Abstract
Stance detection is an important component of understanding hidden influences in everyday life. Since there are thousands of potential topics to take a stance on, most with little to no training data, we focus on zero-shot stance detection: classifying stance from no training examples. In this paper, we present a new dataset for zero-shot stance detection that captures a wider range of topics and lexical variation than in previous datasets. Additionally, we propose a new model for stance detection that implicitly captures relationships between topics using generalized topic representations and show that this model improves performance on a number of challenging linguistic phenomena.
Anthology ID:
2020.emnlp-main.717
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8913–8931
Language:
URL:
https://aclanthology.org/2020.emnlp-main.717
DOI:
10.18653/v1/2020.emnlp-main.717
Bibkey:
Cite (ACL):
Emily Allaway and Kathleen McKeown. 2020. Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8913–8931, Online. Association for Computational Linguistics.
Cite (Informal):
Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations (Allaway & McKeown, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.717.pdf
Video:
 https://slideslive.com/38939177
Code
 emilyallaway/zero-shot-stance
Data
VAST