Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks

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.

[1]  Xin Li,et al.  A Unified Model for Opinion Target Extraction and Target Sentiment Prediction , 2018, AAAI.

[2]  Nanyun Peng,et al.  Cross-Sentence N-ary Relation Extraction with Graph LSTMs , 2017, TACL.

[3]  Xiao-Ming Wu,et al.  Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning , 2018, AAAI.

[4]  Iryna Gurevych,et al.  Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields , 2010, EMNLP.

[5]  Christopher D. Manning,et al.  Graph Convolution over Pruned Dependency Trees Improves Relation Extraction , 2018, EMNLP.

[6]  Yue Zhang,et al.  Sentence-State LSTM for Text Representation , 2018, ACL.

[7]  Ralph Grishman,et al.  Graph Convolutional Networks With Argument-Aware Pooling for Event Detection , 2018, AAAI.

[8]  Li Zhao,et al.  Attention-based LSTM for Aspect-level Sentiment Classification , 2016, EMNLP.

[9]  Richong Zhang,et al.  Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree , 2019, EMNLP.

[10]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[11]  Xiaokui Xiao,et al.  Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms , 2017, AAAI.

[12]  Haris Papageorgiou,et al.  SemEval-2016 Task 5: Aspect Based Sentiment Analysis , 2016, *SEMEVAL.

[13]  Hwee Tou Ng,et al.  An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis , 2019, ACL.

[14]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[15]  Kathleen M. Carley,et al.  Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks , 2019, EMNLP.

[16]  Yang Feng,et al.  Bridging the Gap between Training and Inference for Neural Machine Translation , 2019, ACL.

[17]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[18]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[19]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[20]  Xiaokui Xiao,et al.  Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis , 2016, EMNLP.

[21]  Suresh Manandhar,et al.  SemEval-2014 Task 4: Aspect Based Sentiment Analysis , 2014, *SEMEVAL.

[22]  Yuan Luo,et al.  Graph Convolutional Networks for Text Classification , 2018, AAAI.

[23]  Tieyun Qian,et al.  Transfer Capsule Network for Aspect Level Sentiment Classification , 2019, ACL.

[24]  Jie Zhou,et al.  Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View , 2020, AAAI.

[25]  Erik Cambria,et al.  Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM , 2018, AAAI.

[26]  Philip S. Yu,et al.  Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction , 2018, ACL.

[27]  Danqi Chen,et al.  A Fast and Accurate Dependency Parser using Neural Networks , 2014, EMNLP.

[28]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[29]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[30]  Lidong Bing,et al.  Recurrent Attention Network on Memory for Aspect Sentiment Analysis , 2017, EMNLP.

[31]  Qian Liu,et al.  Improving Opinion Aspect Extraction Using Semantic Similarity and Aspect Associations , 2016, AAAI.

[32]  Man Lan,et al.  Towards a One-stop Solution to Both Aspect Extraction and Sentiment Analysis Tasks with Neural Multi-task Learning , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[33]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.