CrosGrpsABS: Cross-Attention over Syntactic and Semantic Graphs for Aspect-Based Sentiment Analysis in a Low-Resource Language

TL;DR

CrosGrpsABS introduces a hybrid cross-attention framework combining syntactic and semantic graphs with transformer and graph convolutional networks to improve aspect-based sentiment analysis in low-resource languages like Bengali.

Contribution

The paper presents a novel hybrid model that leverages bidirectional cross-attention over syntactic and semantic graphs, specifically designed for low-resource language ABSA tasks.

Findings

Outperforms existing methods on Bengali ABSA datasets

Achieves 0.93% F1-score improvement in Restaurant domain

Gains 1.06% F1-score in Laptop domain on SemEval 2014

Abstract

Aspect-Based Sentiment Analysis (ABSA) is a fundamental task in natural language processing, offering fine-grained insights into opinions expressed in text. While existing research has largely focused on resource-rich languages like English which leveraging large annotated datasets, pre-trained models, and language-specific tools. These resources are often unavailable for low-resource languages such as Bengali. The ABSA task in Bengali remains poorly explored and is further complicated by its unique linguistic characteristics and a lack of annotated data, pre-trained models, and optimized hyperparameters. To address these challenges, this research propose CrosGrpsABS, a novel hybrid framework that leverages bidirectional cross-attention between syntactic and semantic graphs to enhance aspect-level sentiment classification. The CrosGrpsABS combines transformerbased contextual embeddings with graph convolutional networks, built upon rule-based syntactic dependency parsing and semantic similarity computations. By employing bidirectional crossattention, the model effectively fuses local syntactic structure with global semantic context, resulting in improved sentiment classification performance across both low- and high-resource settings. We evaluate CrosGrpsABS on four low-resource Bengali ABSA datasets and the high-resource English SemEval 2014 Task 4 dataset. The CrosGrpsABS consistently outperforms existing approaches, achieving notable improvements, including a 0.93% F1-score increase for the Restaurant domain and a 1.06% gain for the Laptop domain in the SemEval 2014 Task 4 benchmark.