S$^2$GSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Bingfeng, Ouyang, Qihan, Luo, Yongqi, Xu, Boyan, Cai, Ruichu, Hao, Zhifeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914829164347392
author Chen, Bingfeng
Ouyang, Qihan
Luo, Yongqi
Xu, Boyan
Cai, Ruichu
Hao, Zhifeng
author_facet Chen, Bingfeng
Ouyang, Qihan
Luo, Yongqi
Xu, Boyan
Cai, Ruichu
Hao, Zhifeng
contents Previous graph-based approaches in Aspect based Sentiment Analysis(ABSA) have demonstrated impressive performance by utilizing graph neural networks and attention mechanisms to learn structures of static dependency trees and dynamic latent trees. However, incorporating both semantic and syntactic information simultaneously within complex global structures can introduce irrelevant contexts and syntactic dependencies during the process of graph structure learning, potentially resulting in inaccurate predictions. In order to address the issues above, we propose S$^2$GSL, incorporating Segment to Syntactic enhanced Graph Structure Learning for ABSA. Specifically,S$^2$GSL is featured with a segment-aware semantic graph learning and a syntax-based latent graph learning enabling the removal of irrelevant contexts and dependencies, respectively. We further propose a self-adaptive aggregation network that facilitates the fusion of two graph learning branches, thereby achieving complementarity across diverse structures. Experimental results on four benchmarks demonstrate the effectiveness of our framework.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02902
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle S$^2$GSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis
Chen, Bingfeng
Ouyang, Qihan
Luo, Yongqi
Xu, Boyan
Cai, Ruichu
Hao, Zhifeng
Computation and Language
Previous graph-based approaches in Aspect based Sentiment Analysis(ABSA) have demonstrated impressive performance by utilizing graph neural networks and attention mechanisms to learn structures of static dependency trees and dynamic latent trees. However, incorporating both semantic and syntactic information simultaneously within complex global structures can introduce irrelevant contexts and syntactic dependencies during the process of graph structure learning, potentially resulting in inaccurate predictions. In order to address the issues above, we propose S$^2$GSL, incorporating Segment to Syntactic enhanced Graph Structure Learning for ABSA. Specifically,S$^2$GSL is featured with a segment-aware semantic graph learning and a syntax-based latent graph learning enabling the removal of irrelevant contexts and dependencies, respectively. We further propose a self-adaptive aggregation network that facilitates the fusion of two graph learning branches, thereby achieving complementarity across diverse structures. Experimental results on four benchmarks demonstrate the effectiveness of our framework.
title S$^2$GSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis
topic Computation and Language
url https://arxiv.org/abs/2406.02902