The Library
Zero-shot stance detection via contrastive learning
Tools
Liang, Bin, Chen, Zixiao, Gui, Lin, He, Yulan, Yang, Min and Xu, Ruifeng (2022) Zero-shot stance detection via contrastive learning. In: WWW '22: The ACM Web Conference, Online, hosted Lyon, France, 25–29 Apr 2022. Published in: WWW '22: Proceedings of the ACM Web Conference 2022 pp. 2738-2747. ISBN 9781450390965. doi:10.1145/3485447.3511994
|
PDF
WRAP-zero-shot-stance-detection-via-contrastive-learning-2022.pdf - Accepted Version - Requires a PDF viewer. Download (2567Kb) | Preview |
Official URL: https://doi.org/10.1145/3485447.3511994
Abstract
Zero-shot stance detection (ZSSD) is challenging as it requires detecting the stance of previously unseen targets during the inference stage. Being able to detect the target-related transferable stance features from the training data is arguably an important step in ZSSD. Generally speaking, stance features can be grouped into target-invariant and target-specific categories. Target-invariant stance features carry the same stance regardless of the targets they are associated with. On the contrary, target-specific stance features only co-occur with certain targets. As such, it is important to distinguish these two types of stance features when learning stance features of unseen targets. To this end, in this paper, we revisit ZSSD from a novel perspective by developing an effective approach to distinguish the types (target-invariant/-specific) of stance features, so as to better learn transferable stance features. To be specific, inspired by self-supervised learning, we frame the stance-feature-type identification as a pretext task in ZSSD. Furthermore, we devise a novel hierarchical contrastive learning strategy to capture the correlation and difference between target-invariant and -specific features and further among different stance labels. This essentially allows the model to exploit transferable stance features more effectively for representing the stance of previously unseen targets. Extensive experiments on three benchmark datasets show that the proposed framework achieves the state-of-the-art performance in ZSSD.
Item Type: | Conference Item (Paper) | ||||||||||||||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software |
||||||||||||||||||||||||||||||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||||||||||||||||||||||||||||||||
Library of Congress Subject Headings (LCSH): | Natural language processing (Computer science) , Sentiment analysis , Machine translating , Neural networks (Computer science), Machine learning | ||||||||||||||||||||||||||||||||||||
Series Name: | WWW '22 | ||||||||||||||||||||||||||||||||||||
Journal or Publication Title: | WWW '22: Proceedings of the ACM Web Conference 2022 | ||||||||||||||||||||||||||||||||||||
Publisher: | ACM | ||||||||||||||||||||||||||||||||||||
ISBN: | 9781450390965 | ||||||||||||||||||||||||||||||||||||
Official Date: | 25 April 2022 | ||||||||||||||||||||||||||||||||||||
Dates: |
|
||||||||||||||||||||||||||||||||||||
Page Range: | pp. 2738-2747 | ||||||||||||||||||||||||||||||||||||
DOI: | 10.1145/3485447.3511994 | ||||||||||||||||||||||||||||||||||||
Status: | Peer Reviewed | ||||||||||||||||||||||||||||||||||||
Publication Status: | Published | ||||||||||||||||||||||||||||||||||||
Reuse Statement (publisher, data, author rights): | © ACM 2022. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in WWW '22: The ACM Web Conference Proceedings, http://dx.doi.org/10.1145/3485447.3511994 | ||||||||||||||||||||||||||||||||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||||||||||||||||||||||||||||||||
Date of first compliant deposit: | 16 March 2022 | ||||||||||||||||||||||||||||||||||||
Date of first compliant Open Access: | 17 March 2022 | ||||||||||||||||||||||||||||||||||||
RIOXX Funder/Project Grant: |
|
||||||||||||||||||||||||||||||||||||
Conference Paper Type: | Paper | ||||||||||||||||||||||||||||||||||||
Title of Event: | WWW '22: The ACM Web Conference | ||||||||||||||||||||||||||||||||||||
Type of Event: | Conference | ||||||||||||||||||||||||||||||||||||
Location of Event: | Online, hosted Lyon, France | ||||||||||||||||||||||||||||||||||||
Date(s) of Event: | 25–29 Apr 2022 | ||||||||||||||||||||||||||||||||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year