Extensible Multi-Granularity Fusion Network for Aspect-based Sentiment Analysis
This work addresses a scalability problem for researchers and practitioners in ABSA by providing a framework to efficiently integrate multiple features without extra computational cost, though it appears incremental as it builds on existing methods like GNNs and knowledge graphs.
The paper tackles the lack of a scalable framework for integrating diverse linguistic and structural features in Aspect-based Sentiment Analysis (ABSA) by proposing the Extensible Multi-Granularity Fusion (EMGF) network, which combines dependency and constituent syntactic, attention semantic, and external knowledge graphs, achieving superior performance on SemEval 2014 and Twitter datasets.
Aspect-based Sentiment Analysis (ABSA) evaluates sentiment expressions within a text to comprehend sentiment information. Previous studies integrated external knowledge, such as knowledge graphs, to enhance the semantic features in ABSA models. Recent research has examined the use of Graph Neural Networks (GNNs) on dependency and constituent trees for syntactic analysis. With the ongoing development of ABSA, more innovative linguistic and structural features are being incorporated (e.g. latent graph), but this also introduces complexity and confusion. As of now, a scalable framework for integrating diverse linguistic and structural features into ABSA does not exist. This paper presents the Extensible Multi-Granularity Fusion (EMGF) network, which integrates information from dependency and constituent syntactic, attention semantic , and external knowledge graphs. EMGF, equipped with multi-anchor triplet learning and orthogonal projection, efficiently harnesses the combined potential of each granularity feature and their synergistic interactions, resulting in a cumulative effect without additional computational expenses. Experimental findings on SemEval 2014 and Twitter datasets confirm EMGF's superiority over existing ABSA methods.