OpenStance: Real-world Zero-shot Stance Detection

10/25/2022
by   Hanzi Xu, et al.
1

Prior studies of zero-shot stance detection identify the attitude of texts towards unseen topics occurring in the same document corpus. Such task formulation has three limitations: (i) Single domain/dataset. A system is optimized on a particular dataset from a single domain; therefore, the resulting system cannot work well on other datasets; (ii) the model is evaluated on a limited number of unseen topics; (iii) it is assumed that part of the topics has rich annotations, which might be impossible in real-world applications. These drawbacks will lead to an impractical stance detection system that fails to generalize to open domains and open-form topics. This work defines OpenStance: open-domain zero-shot stance detection, aiming to handle stance detection in an open world with neither domain constraints nor topic-specific annotations. The key challenge of OpenStance lies in the open-domain generalization: learning a system with fully unspecific supervision but capable of generalizing to any dataset. To solve OpenStance, we propose to combine indirect supervision, from textual entailment datasets, and weak supervision, from data generated automatically by pre-trained Language Models. Our single system, without any topic-specific supervision, outperforms the supervised method on three popular datasets. To our knowledge, this is the first work that studies stance detection under the open-domain zero-shot setting. All data and code are publicly released.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/14/2021

Adversarial Learning for Zero-Shot Stance Detection on Social Media

Stance detection on social media can help to identify and understand sla...
research
11/06/2019

Open Domain Web Keyphrase Extraction Beyond Language Modeling

This paper studies keyphrase extraction in real-world scenarios where do...
research
10/07/2020

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

Stance detection is an important component of understanding hidden influ...
research
10/29/2022

Beyond prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations

Recent work has demonstrated that pre-trained language models (PLMs) are...
research
02/01/2023

Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization

Image geolocalization is the challenging task of predicting the geograph...
research
06/29/2023

Towards Open-Domain Topic Classification

We introduce an open-domain topic classification system that accepts use...
research
08/18/2022

Exploiting Sentiment and Common Sense for Zero-shot Stance Detection

The stance detection task aims to classify the stance toward given docum...

Please sign up or login with your details

Forgot password? Click here to reset