Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks
This work addresses the challenge of precisely connecting aspect and sentiment analysis in NLP, offering an incremental improvement over existing methods for researchers and practitioners in sentiment analysis.
The paper tackles the problem of jointly modeling aspect extraction and sentiment detection in target-based sentiment analysis by proposing a dynamic heterogeneous graph neural network that allows aspect words to interact with sentiment information. The model outperforms state-of-the-art methods on benchmark datasets, with significant gains on challenging instances involving multiple or no-opinion aspects.
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.