Zero-Shot Stance Detection: A Dataset and Model Using Generalized Topic Representations
By Emily Allaway, K. McKeown. 2020
251 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Natural Language Processing, Sentiment & Opinion Analysis
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Zheng Zhang
- Ruiqi Zhong
- Daniel Klein
- Luke S. Zettlemoyer
- Kristy Lee
- Hannaneh Hajishirzi
- Jianfeng Gao
- Mohit Bansal
In Natural Language Processing
- Ruiqi Zhong
- Zheng Zhang
- Kristy Lee
- Daniel Klein
- Christopher D. Manning
- Luke S. Zettlemoyer
- Percy Liang
- Mirella Lapata
Citations in the corpus
- Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections (2021, background): “Additionally, some datasets contain thousands of labels (Chalkidis et al., 2019; Allaway and McKeown, 2020).”
- Meta-tuning Language Models to Answer Prompts Better (2021, background): “Additionally, some datasets contain thousands of labels (Chalkidis et al., 2019; Allaway and McKeown, 2020).”