Saved in:
Bibliographic Details
Main Authors: Cheng, Zhenxiao, Zhou, Jie, Wu, Wen, Chen, Qin, He, Liang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.18145
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914693846663168
author Cheng, Zhenxiao
Zhou, Jie
Wu, Wen
Chen, Qin
He, Liang
author_facet Cheng, Zhenxiao
Zhou, Jie
Wu, Wen
Chen, Qin
He, Liang
contents 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 (\texttt{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 \texttt{IBG} approach considerably improves both the models' performance and interpretability by identifying sentiment-aware features.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18145
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis
Cheng, Zhenxiao
Zhou, Jie
Wu, Wen
Chen, Qin
He, Liang
Computation and Language
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 (\texttt{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 \texttt{IBG} approach considerably improves both the models' performance and interpretability by identifying sentiment-aware features.
title Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis
topic Computation and Language
url https://arxiv.org/abs/2402.18145