Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks
By Chen Zhang, Qiuchi Li, Dawei Song. 2019
524 citations recorded by the source corpus.
Due to their inherent capability in semantic alignment of aspects and their context words, attention mechanism and Convolutional Neural Networks (CNNs) are widely applied for aspect-based sentiment classification. However, these models lack a mechanism to account for relevant syntactical constraints and long-range word dependencies, and hence may mistakenly recognize syntactically irrelevant contextual words as clues for judging aspect sentiment. To tackle this problem, we propose to build a Graph Convolutional Network (GCN) over the dependency tree of a sentence to exploit syntactical information and word dependencies. Based on it, a novel aspect-specific sentiment classification framework is raised. Experiments on three benchmarking collections illustrate that our proposed model has comparable effectiveness to a range of state-of-the-art models, and further demonstrate that both syntactical information and long-range word dependencies are properly captured by the graph convolution structure.
Subfields: Artificial Intelligence, Graph Learning, Sentiment & Opinion Analysis
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
In Graph Learning
Citations in the corpus
- Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification (2020, methodology): “We compare the proposed DGEDT∗ with a line of baselines and state-of-the-art alternatives, including LSTM, MemNet (Tang et al., 2016b), AOA (Huang et al., 2018), IAN (Ma et al., 2017), TNetLF (Li et al., 2018), CAPSNet (Chen and Qian, 2019), Transfer-CAPS (Chen and Qian, 2019), TGBERT (Gao et al., 2”
- Exploiting BERT for End-to-End Aspect-based Sentiment Analysis (2019, background): “…Majumder et al., 2018; Li et al., 2018; He et al., 2018; Xue and Li, 2018; Wang et al., 2018; Fan et al., 2018; Huang and Carley, 2018; Lei et al., 2019; Li et al., 2019b; Zhang et al., 2019) 2 , but the improvement of these models measured by the accuracy or F1 score has reached a bottleneck.”
- Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, unknown): “graph networks based on dependency tree are proposed to model the structure of a sentence through the dependency tree of the sentence [10, 11].”
- Graph Sequential Network for Reasoning over Sequences (2020, methodology): “Zhang et al. (2019) proposed to use GCN over syntactic dependency trees for aspect-based sentiment classifi-cation.”
- A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges (2022, methodology): “Aspect Sentiment Classification (ASC) AdaRNN [49], Target-dep [50], TC-LSTM [51], ATAE-LSTM [52], MemNet [53], IAN [54], BILSTM-ATT-G [55], RAM [56], HEAT [57], GCAE [58], TNet [59], MGAN [60], PWCN [61], BERT-pair [62], TransCap [63], IACapsNet [64], AGDT [65], ASGCN [66], CDT [67], DGEDT [68], kum”
- Relational Graph Attention Network for Aspect-based Sentiment Analysis (2020, methodology): “Second, if an aspect contains more than 2We set n = ∞ if the distance is longer than 4. one word, the dependency relations will be aggregated at the aspect, unlike in (Zhang et al., 2019; Sun et al., 2019b) which require extra pooling or attention operations.”