Isomer: Transfer enhanced Dual-Channel Heterogeneous Dependency Attention Network for Aspect-based Sentiment Classification

TL;DR

Isomer is a novel dual-channel attention network that leverages heterogeneous dependency graphs with external knowledge to improve aspect-based sentiment classification, addressing limitations of previous homogeneous graph approaches.

Contribution

The paper introduces a transfer-enhanced dual-channel heterogeneous dependency attention network that effectively models short texts with diverse information types and external knowledge.

Findings

Outperforms recent models on benchmark datasets

Effectively captures importance of various information features

Enhances contextual feature integration in sentiment analysis

Abstract

Aspect-based sentiment classification aims to predict the sentiment polarity of a specific aspect in a sentence. However, most existing methods attempt to construct dependency relations into a homogeneous dependency graph with the sparsity and ambiguity, which cannot cover the comprehensive contextualized features of short texts or consider any additional node types or semantic relation information. To solve those issues, we present a sentiment analysis model named Isomer, which performs a dual-channel attention on heterogeneous dependency graphs incorporating external knowledge, to effectively integrate other additional information. Specifically, a transfer-enhanced dual-channel heterogeneous dependency attention network is devised in Isomer to model short texts using heterogeneous dependency graphs. These heterogeneous dependency graphs not only consider different types of information but also incorporate external knowledge. Experiments studies show that our model outperforms recent models on benchmark datasets. Furthermore, the results suggest that our method captures the importance of various information features to focus on informative contextual words.