Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification

By Hao Tang, Donghong Ji, Chenliang Li, Qiji Zhou. Annual Meeting of the Association for Computational Linguistics, 2020

387 citations recorded by the source corpus.

Aspect-based sentiment classification is a popular task aimed at identifying the corresponding emotion of a specific aspect. One sentence may contain various sentiments for different aspects. Many sophisticated methods such as attention mechanism and Convolutional Neural Networks (CNN) have been widely employed for handling this challenge. Recently, semantic dependency tree implemented by Graph Convolutional Networks (GCN) is introduced to describe the inner connection between aspects and the associated emotion words. But the improvement is limited due to the noise and instability of dependency trees. To this end, we propose a dependency graph enhanced dual-transformer network (named DGEDT) by jointly considering the flat representations learnt from Transformer and graph-based representations learnt from the corresponding dependency graph in an iterative interaction manner. Specifically, a dual-transformer structure is devised in DGEDT to support mutual reinforcement between the flat representation learning and graph-based representation learning. The idea is to allow the dependency graph to guide the representation learning of the transformer encoder and vice versa. The results on five datasets demonstrate that the proposed DGEDT outperforms all state-of-the-art alternatives with a large margin.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/57fff1bd2265848f126f7f62b10d1c67cb6be0da

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Eduard H. Hovy
2. Hao Chen
3. Xiaojie Wang
4. Zhanyu Ma
5. Ruifan Li
6. Fangxiang Feng
7. Ani Nenkova
8. Mirella Lapata

Citations in the corpus

• Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, neutral): “• DGEDT [30] learns the flat representation and graph-based representation by a dependency graph enhanced dual-transformer network.”
• Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (2021, methodology): “12) DGEDT (Tang et al., 2020) proposes a dependency graph enhanced dual-transformer network by jointly considering flat representations and graphbased representations.”