Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis

Zhenxiao Cheng, Jie Zhou, Wen Wu, Qin Chen, Liang He

Abstract
Gradient-based explanation methods are increasingly used to interpret neural models in natural language processing (NLP) due to their high fidelity. Such methods determine word-level importance using dimension-level gradient values through a norm function, often presuming equal significance for all gradient dimensions. However, in the context of Aspect-based Sentiment Analysis (ABSA), our preliminary research suggests that only specific dimensions are pertinent. To address this, we propose the Information Bottleneck-based Gradient (IBG) explanation framework for ABSA. This framework leverages an information bottleneck to refine word embeddings into a concise intrinsic dimension, maintaining essential features and omitting unrelated information. Comprehensive tests show that our IBG approach considerably improves both the models’ performance and the explanations’ clarity by identifying sentiment-aware features.
Anthology ID:
2024.lrec-main.897
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
10274–10285
Language:
URL:
https://aclanthology.org/2024.lrec-main.897
DOI:
Bibkey:
Cite (ACL):
Zhenxiao Cheng, Jie Zhou, Wen Wu, Qin Chen, and Liang He. 2024. Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10274–10285, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis (Cheng et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.lrec-main.897.pdf
PDF Search