Learn from Structural Scope: Improving Aspect-Level Sentiment Analysis with Hybrid Graph Convolutional Networks

27 Apr 2022  ·  Lvxiaowei Xu, Xiaoxuan Pang, Jianwang Wu, Ming Cai, Jiawei Peng ·

Aspect-level sentiment analysis aims to determine the sentiment polarity towards a specific target in a sentence. The main challenge of this task is to effectively model the relation between targets and sentiments so as to filter out noisy opinion words from irrelevant targets. Most recent efforts capture relations through target-sentiment pairs or opinion spans from a word-level or phrase-level perspective. Based on the observation that targets and sentiments essentially establish relations following the grammatical hierarchy of phrase-clause-sentence structure, it is hopeful to exploit comprehensive syntactic information for better guiding the learning process. Therefore, we introduce the concept of Scope, which outlines a structural text region related to a specific target. To jointly learn structural Scope and predict the sentiment polarity, we propose a hybrid graph convolutional network (HGCN) to synthesize information from constituency tree and dependency tree, exploring the potential of linking two syntax parsing methods to enrich the representation. Experimental results on four public datasets illustrate that our HGCN model outperforms current state-of-the-art baselines.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Aspect-Based Sentiment Analysis (ABSA) Lap14 HGCN Acc 78.64 # 1
Aspect-Based Sentiment Analysis (ABSA) Rest14 HGCN Acc 84.09 # 1
Aspect-Based Sentiment Analysis (ABSA) Rest15 HGCN Acc 82.66 # 1
Aspect-Based Sentiment Analysis (ABSA) Rest16 HGCN Acc 89.84 # 1

Methods


No methods listed for this paper. Add relevant methods here