To be Closer: Learning to Link up Aspects with Opinions

Dependency parse trees are helpful for discovering the opinion words in aspect-based sentiment analysis (ABSA) (Huang and Carley, 2019). However, the trees obtained from offthe-shelf dependency parsers are static, and could be sub-optimal in ABSA. This is because the syntactic trees are not designed for capturing the interactions between opinion words and aspect words. In this work, we aim to shorten the distance between aspects and corresponding opinion words by learning an aspect-centric tree structure. The aspect and opinion words are expected to be closer along such tree structure compared to the standard dependency parse tree. The learning process allows the tree structure to adaptively correlate the aspect and opinion words, enabling us to better identify the polarity in the ABSA task. We conduct experiments on five aspectbased sentiment datasets, and the proposed model significantly outperforms recent strong baselines. Furthermore, our thorough analysis demonstrates the average distance between aspect and opinion words are shortened by at least 19% on the standard SemEval Restaurant14 (Pontiki et al., 2014) dataset.

[1]  Ming Zhou,et al.  Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification , 2014, ACL.

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

[3]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[4]  Lysandre Debut,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

[5]  Shuai Wang,et al.  Target-Sensitive Memory Networks for Aspect Sentiment Classification , 2018, ACL.

[6]  Wei Lu,et al.  Reasoning with Latent Structure Refinement for Document-Level Relation Extraction , 2020, ACL.

[7]  Claire Cardie,et al.  Towards Dynamic Computation Graphs via Sparse Latent Structure , 2018, EMNLP.

[8]  Kai Wang,et al.  Relational Graph Attention Network for Aspect-based Sentiment Analysis , 2020, ACL.

[9]  Luyao Huang,et al.  Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence , 2019, NAACL.

[10]  Ting Liu,et al.  Aspect Level Sentiment Classification with Deep Memory Network , 2016, EMNLP.

[11]  Alexander M. Rush,et al.  A Tutorial on Deep Latent Variable Models of Natural Language , 2018, ArXiv.

[12]  Wei Lu,et al.  Learning Latent Opinions for Aspect-level Sentiment Classification , 2018, AAAI.

[13]  Frank Harary,et al.  Graph Theory , 2016 .

[14]  Wei Lu,et al.  Learning Latent Forests for Medical Relation Extraction , 2020, IJCAI.

[15]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[16]  Wei Lu,et al.  Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems , 2019, ACL.

[17]  Navneet Kaur,et al.  Opinion mining and sentiment analysis , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[18]  Suresh Manandhar,et al.  SemEval-2015 Task 12: Aspect Based Sentiment Analysis , 2015, *SEMEVAL.

[19]  Arthur Mensch,et al.  Differentiable Dynamic Programming for Structured Prediction and Attention , 2018, ICML.

[20]  Wei Lu,et al.  Dependency-Guided LSTM-CRF for Named Entity Recognition , 2019, EMNLP.

[21]  Xin Li,et al.  Transformation Networks for Target-Oriented Sentiment Classification , 2018, ACL.

[22]  Yue Zhang,et al.  Attention Modeling for Targeted Sentiment , 2017, EACL.

[23]  Ivan Titov,et al.  Interpretable Neural Predictions with Differentiable Binary Variables , 2019, ACL.

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

[25]  Alexander M. Rush,et al.  Structured Attention Networks , 2017, ICLR.

[26]  Stephen Clark,et al.  Jointly learning sentence embeddings and syntax with unsupervised Tree-LSTMs , 2017, Natural Language Engineering.

[27]  Hao Li,et al.  Learning Explicit and Implicit Structures for Targeted Sentiment Analysis , 2019, EMNLP/IJCNLP.

[28]  Lidong Bing,et al.  Better Feature Integration for Named Entity Recognition , 2021, NAACL.

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

[30]  Yang Liu,et al.  Learning Structured Text Representations , 2017, TACL.

[31]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[32]  Xavier Carreras,et al.  Structured Prediction Models via the Matrix-Tree Theorem , 2007, EMNLP.

[33]  Mi Zhang,et al.  Convolution over Hierarchical Syntactic and Lexical Graphs for Aspect Level Sentiment Analysis , 2020, EMNLP.

[34]  André F. T. Martins,et al.  Latent Structure Models for Natural Language Processing , 2019, ACL.

[35]  Aspect Sentiment Classification with Aspect-Specific Opinion Spans , 2020, EMNLP.

[36]  Xiaobing Sun,et al.  Understanding Attention for Text Classification , 2020, ACL.

[37]  Philip S. Yu,et al.  BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis , 2019, NAACL.

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

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

[40]  Zhiyang Teng,et al.  Inducing Target-specific Latent Structures for Aspect Sentiment Classification , 2020, EMNLP.

[41]  Lu Xu,et al.  Position-Aware Tagging for Aspect Sentiment Triplet Extraction , 2020, EMNLP.

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