SHIJINGLI0206 / Aspect-Based-Sentiment-Analysis

A paper list for aspect based sentiment analysis and emotion-cause pair extraction.

Aspect-Based-Sentiment-Analysis && Emotion-Cause Pair Extraction

Datasets

Aspect-based Sentiment Analysis

• [SemEval-14]: SemEval-2014 Task 4: Aspect Based Sentiment Analysis. [paper] [data]

• [ACL-14]: Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification. [paper] [data]

• [EMNLP-19]: A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis. [paper] [data]

Targeted-based Sentiment Analysis

• [COLING-16]: Sentihood: Targeted aspect based sentiment analysis dataset for urban neighbourhoods. [paper] [data]

Aspect Term Extraction

• [AAAI-19]: A Unified Model for Opinion Target Extraction and Target Sentiment Prediction. [paper] [code]

• [NAACL-19]: Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling. [paper] [data]

Targeted Sentiment Analysis

• [EMNLP-13]: Open Domain Targeted Sentiment.[paper]

ARTS(Adversarial datasets)

• [EMNLP-20]: Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis.[paper]

Emotion-cause Pair Extraction

• [ACL-19]: Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts. [paper] [code][data]

Paper List

Emotion-Cause Pair Extraction

• [ACL-19]: Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts. [paper] [code]

• [Arxiv-20]: End-to-end Emotion-Cause Pair Extraction via Learning to Link. [paper]

• [Arxiv-20]: ECSP: A New Task for Emotion-Cause Span-Pair Extraction and Classification . [paper]

• [Neurocomputing-20]: Joint Multi-level Attentional Model for Emotion Detection and Emotion-cause Pair Extraction. [paper]

• [ACL-20]: ECPE-2D: Emotion-Cause Pair Extraction based on Joint Two-Dimensional Representation, Interaction and Prediction. [paper]

• [ACL-20]: Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction. [paper]

• [ACL-20]: Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction. [paper]

• [EMNLP-20]: Emotion-Cause Pair Extraction as Sequence Labeling Based on A Novel Tagging Scheme. [paper]

• [EMNLP-20]: End-to-End Emotion-Cause Pair Extraction based on Sliding Window Multi-Label Learning. [paper]

• [COLING-20]: A Symmetric Local Search Network for Emotion-Cause Pair Extraction. [paper]

• [COLING-20]: End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network. [paper]

SemEval-2014 Task 4

Subtask 1: Unsupervised aspect extraction

• [ACL-17]: An Unsupervised Neural Attention Model for Aspect Extraction. [paper] [code]

• [EMNLP-18]: Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised.[paper]

• [IJCAI-19]: Unsupervised Neural Aspect Extraction with Sememes.[paper]

• [EMNLP-19]: Coupling Global and Local Context for Unsupervised Aspect Extraction.[paper]

• [EMNLP-19]: Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training.[paper]

• [ACL-20]: Embarrassingly Simple Unsupervised Aspect Extraction.[paper]

• [EMNLP-20]: Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding. [paper]

Subtask 2: Aspect term extraction

• [AAAI-17]: Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms. [paper]

• [IJCAI-18]: Aspect Term Extraction with History Attention and Selective Transformation. [paper]

• [ACL-18]: Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction. [paper] [code]

• [ACL-19]: Exploring Sequence-to-Sequence Learning in Aspect Term Extraction. [paper]

• [ACL-19]: Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision.[paper][code]

• [ACL-20]: Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation. [paper]

• [EMNLP-20]: Enhancing Aspect Term Extraction with Soft Prototypes. [paper]

• [COLING-20]: Constituency Lattice Encoding for Aspect Term Extraction. [paper]

• [COLING-20]: POD: Positional Dependency-Based Word Embedding for Aspect Term Extraction. [paper]

• [COLING-20]: Syntactically Aware Cross-Domain Aspect and Opinion Terms Extraction. [paper]

• [AAAI-19]: A Unified Model for Opinion Target Extraction and Target Sentiment Prediction. [paper] [code]

• [ACL-19]: DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction. [paper] [code]

• [ACL-19]: An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis. [paper] [code]

• [ACL-19]: Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification. [paper] [code]

• [EMNLP-19]: Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning. [paper] [code]

• [AAAI-20]: Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis. [paper]

• [AAAI-20]: Target-Aspect-Sentiment Joint Detection for Aspect-Based Sentiment Analysis. [paper][code]

• [Arxiv-20]: Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks. [paper]

• [Arxiv-20]: An Iterative Knowledge Transfer Network with Routing for Aspect-based Sentiment Analysis. [paper]

• [Arxiv-20]: A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis. [paper]

Subtask 3: Aspect-based sentiment analysis

• [ACL-14]: Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification. [paper] [data]

• [NIPS-14-workshop]: Aspect Specific Sentiment Analysis using Hierarchical Deep Learning. [paper]

• [EMNLP-15]: PhraseRNN: Phrase Recursive Neural Network for Aspect-based Sentiment Analysis. [paper]

• [COLING-16]: Effective LSTMs for Target-Dependent Sentiment Classification. [paper] [data]

• [EMNLP-16]: Aspect Level Sentiment Classification with Deep Memory Network. [paper] [code]

• [EMNLP-16]: Attention-based LSTM for Aspect-level Sentiment Classification. [paper] [code]

• [EMNLP-16]: A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis. [paper]

• [EMNLP-16]: Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis. [paper]

• [IJCAI-17]: Interactive Attention Networks for Aspect-Level Sentiment Classification. [paper] [code]

• [CIKM-17]: Dyadic Memory Networks for Aspect-based Sentiment Analysis. [paper]

• [EMNLP-17]: Recurrent Attention Network on Memory for Aspect Sentiment Analysis. [paper] [code]

• [WWW-18]: Content Attention Model for Aspect Based Sentiment Analysis. [paper] [code]

• [AAAI-18]: Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis. [paper]

• [AAAI-18]: Learning Latent Opinions for Aspect-Level Sentiment Classification. [paper]

• [ACL-18]: Exploiting Document Knowledge for Aspect-level Sentiment Classification. [paper] [code]

• [ACL-18]: Target-Sensitive Memory Networks for Aspect Sentiment Classification. [paper]

• [ACL-18]: Aspect Based Sentiment Analysis with Gated Convolutional Networks. [paper] [code]

• [ACL-18]: Transformation Networks for Target-Oriented Sentiment Classification. [paper] [code]

• [IJCAI-18]: Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks. [paper]

• [COLING-18]: Effective Attention Modeling for Aspect-Level Sentiment Classification. [paper]

• [COLING-18]: Enhanced Aspect Level Sentiment Classification with Auxiliary Memory. [paper] [code]

• [COLING-18]: A Position-aware Bidirectional Attention Network for Aspect-levelSentiment Analysis. [paper]

• [EMNLP-18]: Joint Aspect and Polarity Classification for Aspect-based Sentiment Analysis with End-to-End Neural Networks. [paper]

• [EMNLP-18]: Multi-grained Attention Network for Aspect-Level Sentiment Classification. [paper] [code]

• [EMNLP-18]: Parameterized Convolutional Neural Networks for Aspect LevelSentiment Classification. [paper]

• [SBP-BRiMS-18]: Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks. [paper] [code]

• [AAAI-19]: Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification. [paper] [data]

• [NAACL-19]: BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis. [paper] [code]

• [NAACL-19]: Utilizing BERT for Aspect-Based Sentiment Analysisvia Constructing Auxiliary Sentence. [paper] [code]

• [ACL-19]: Progressive Self-Supervised Attention Learning forAspect-Level Sentiment Analysis. [paper] [code]

• [ACL-19]: Transfer Capsule Network for Aspect Level Sentiment Classification. [paper] [code]

• [EMNLP-19]: Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks. [paper] [code]

• [EMNLP-19]: Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree. [paper] [code]

• [EMNLP-19]: Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification. [paper]

• [EMNLP-19]: A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis. [paper] [code]

• [EMNLP-19]: Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks. [paper]

• [EMNLP-19]: A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis. [paper] [code]

• [arXiv-19]: Attentional Encoder Network for Targeted Sentiment Classification. [paper] [code]

• [arXiv-19]: Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification. [paper] [code]

• [arXiv-19]: A Failure of Aspect Sentiment Classifiers and an Adaptive Re-weighting Solution. [paper]

• [AAAI-20]: Replicate, Walk, and Stop on Syntax: an Effective Neural Network Model for Aspect-Level Sentiment Classification. [paper][code]

• [arXiv-20]: Exploiting Typed Syntactic Dependencies for Targeted Sentiment Classification Using Graph Attention Neural Network. [paper]

• [ACL-20]: Relational Graph Attention Network for Aspect-based Sentiment Analysis. [paper][code]

• [ACL-20]: Aspect Sentiment Classification with Document-level Sentiment Preference Modeling. [paper]

• [ACL-20]: Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification. [paper]

• [ACL-20]: Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis. [paper]

• [ACL-20]: Relation-Aware Collaborative Learning for Unified Aspect-Based Sentiment Analysis. [paper]

• [EMNLP-20]: Convolution over Hierarchical Syntactic and Lexical Graphs for Aspect Level Sentiment Analysis. [paper]

• [EMNLP-20]: Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis. [paper]

• [EMNLP-20]: Aspect Sentiment Classification with Aspect-Specific Opinion Spans. [paper]

• [EMNLP-20]: Inducing Target-Specific Latent Structures for Aspect Sentiment Classification. [paper]

• [EMNLP-20]: A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysis. [paper]

• [Finding of EMNLP-20]: GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis. [paper]

• [Finding of EMNLP-20]: Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis. [paper]

• [Finding of EMNLP-20]: DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis. [paper]

• [Finding of EMNLP-20]: Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation. [paper]

• [COLING-20]: Jointly Learning Aspect-Focused and Inter-Aspect Relations with Graph Convolutional Networks for Aspect Sentiment Analysis. [paper]

• [COLING-20]: METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis. [paper]

• [COLING-20]: Regrexit or not Regrexit: Aspect-based Sentiment Analysis in Polarized Contexts. [paper]

• [COLING-20]: Understanding Pre-trained BERT for Aspect-based Sentiment Analysis. [paper]

• [COLING-20]: Joint Aspect Extraction and Sentiment Analysis with Directional Graph Convolutional Networks. [paper]

• [COLING-20]:Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification. [paper]

• [COLING-20]:Attention Transfer Network for Aspect-level Sentiment Classification. [paper]

• [COLING-20]:Label Correction Model for Aspect-based Sentiment Analysis. [paper]

• [COLING-20]:Aspect-Category based Sentiment Analysis with Hierarchical Graph Convolutional Network. [paper]

• [COLING-20]:Building Large-Scale English and Korean Datasets for Aspect-Level Sentiment Analysis in Automotive Domain. [paper]

Subtask 4: Multi-Aspect Sentiment Analysis

• [NAACL-18]: Modeling Inter-Aspect Dependencies for Aspect-Based Sentiment Analysis. [paper]

• [EMNLP-18]: IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis. [paper] [code]

• [EMNLP-18]: Document-level multi-aspect sentiment classification as machine comprehension. [paper] [code]

• [COLING-18]: Document-level Multi-aspect Sentiment Classification by Jointly Modeling Users, Aspects, and Overall Ratings. [paper][code]

• [NAACL-19]: A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification. [paper][code]

• [EMNLP-19]: CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis. [paper]

• [EMNLP-19]: Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning. [paper]

• [CIKM-19]: Document-Level Multi-Aspect Sentiment Classification for Online Reviews of Medical Experts. [paper]

• [EMNLP-20]: Diversified Multiple Instance Learning for Document-Level Multi-Aspect Sentiment Classification. [paper]

Subtask 5: Aspect Sentiment Analysis Towards Question Answering

• [EMNLP-18]: Sentiment Classification towards Question-Answering with Hierarchical Matching Network. [paper]

• [ACL-19]: Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network. [paper]

Subtask 6: Cross-domain Aspect-based Sentiment Analysis

• [EMNLP-19]: Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification. [paper]

• [EMNLP-20]: Unified Feature and Instance Based Domain Adaptation for Aspect-Based Sentiment Analysis. [paper]

Subtask 7: Target-oriented Opinion Words Extraction

• [NAACL-19]: Target-oriented Opinion Words Extraction with Target-fused NeuralSequence Labeling. [paper] [code]

• [AAAI-20]: Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction. [paper]

• [ACL-20]: SpanMlt: A Span-based Multi-Task Learning Framework for Pair-wise Aspect and Opinion Terms Extraction. [paper]

• [ACL-20]: Synchronous Double-channel Recurrent Network for Aspect-Opinion Pair Extraction. [paper]

• [EMNLP-20]: Position-Aware Tagging for Aspect Sentiment Triplet Extraction. [paper]

• [EMNLP-20]: Deep Weighted MaxSAT for Aspect-based Opinion Extraction. [paper]

• [EMNLP-20]: Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning. [paper]

• [Finding of EMNLP-20]: Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction. [paper]

Subtask 8: Targeted Sentiment Analysis

• [EMNLP-13]: Open Domain Targeted Sentiment.[paper]

• [EMNLP-16]: Neural Networks for Open Domain Targeted Sentiment.[paper]

• [AAAI-17]: Learning Latent Sentiment Scopes for Entity-Level Sentiment Analysis.[paper]

• [EMNLP-18]: Joint Learning for Targeted Sentiment Analysis. [paper]

• [EMNLP-19]: Learning Explicit and Implicit Structures for Targeted Sentiment Analysis. [paper] [code]

• [Finding of EMNLP-20]: A Shared-Private Representation Model with Coarse-to-Fine Extraction for Target Sentiment Analysis. [paper] [code]

Subtask 9: Targeted-based Sentiment Analysis

• [COLING-16]: Sentihood: Targeted aspect based sentiment analysis dataset for urban neighbourhoods. [paper] [data]

• [AAAI-18]: Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM. [paper]

• [NAACL-18]: Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis. [paper] [code]

• [ACL-19]: Context-aware Embedding for Targeted Aspect-based Sentiment Analysis. [paper]