Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks

Abstract

Target-Based Sentiment Analysis aims to detect the opinion aspects (aspect extraction) and the sentiment polarities (sentiment detection) towards them. Both the previous pipeline and integrated methods fail to precisely model the innate connection between these two objectives. In this paper, we propose a novel dynamic heterogeneous graph to jointly model the two objectives in an explicit way. Both the ordinary words and sentiment labels are treated as nodes in the heterogeneous graph, so that the aspect words can interact with the sentiment information. The graph is initialized with multiple types of dependencies, and dynamically modified during real-time prediction. Experiments on the benchmark datasets show that our model outperforms the state-of-the-art models. Further analysis demonstrates that our model obtains significant performance gain on the challenging instances under multiple-opinion aspects and no-opinion aspect situations.

References in corpus (8)

• Semi-Supervised Classification with Graph Convolutional Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Spectral Networks and Locally Connected Networks on Graphs
• Gated Graph Sequence Neural Networks
• Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
• Sentence-State LSTM for Text Representation
• Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks
• An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

Cited by in corpus (1)

• GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis