Isomer: Transfer enhanced Dual-Channel Heterogeneous Dependency Attention Network for Aspect-based Sentiment Classification
This work addresses aspect-based sentiment classification for natural language processing applications, but it appears incremental as it builds on existing graph-based methods by incorporating heterogeneous dependencies and external knowledge.
The paper tackles the problem of aspect-based sentiment classification by addressing the limitations of homogeneous dependency graphs, which often suffer from sparsity and ambiguity, by proposing Isomer, a model that uses dual-channel attention on heterogeneous dependency graphs with external knowledge, and it reports outperforming recent models on benchmark datasets.
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.