SenticVec: Toward Robust and Human-Centric Neurosymbolic Sentiment Analysis

Xulang Zhang, Rui Mao, Erik Cambria


Abstract
The success of state-of-the-art Natural Language Processing (NLP) systems heavily depends on deep neural networks, which excel in various tasks through strong data fitting and latent feature modeling abilities. However, certain challenges linked to deep neural networks and supervised deep learning deserve considerations, e.g., extensive computing resources, knowledge forgetting, etc. Previous research attempted to tackle these challenges individually through irrelative techniques. However, they do not instigate fundamental shifts in the learning paradigm. In this work, we propose a novel neurosymbolic method for sentiment analysis to tackle these issues. We also propose a novel sentiment-pragmatic knowledge base that places emphasis on human subjectivity within varying domain annotations. We conducted extensive experiments to show that our neurosymbolic framework for sentiment analysis stands out for its lightweight nature, robustness across domains and languages, efficient few-shot training, and rapid convergence.
Anthology ID:
2024.findings-acl.289
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4851–4863
Language:
URL:
https://aclanthology.org/2024.findings-acl.289
DOI:
10.18653/v1/2024.findings-acl.289
Bibkey:
Cite (ACL):
Xulang Zhang, Rui Mao, and Erik Cambria. 2024. SenticVec: Toward Robust and Human-Centric Neurosymbolic Sentiment Analysis. In Findings of the Association for Computational Linguistics ACL 2024, pages 4851–4863, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
SenticVec: Toward Robust and Human-Centric Neurosymbolic Sentiment Analysis (Zhang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.findings-acl.289.pdf