Repository files navigation

Papers, models and datasets for Aspect-Category Sentiment Analysis, which contains two fine-grained subtasks: Aspect Category Detection (ACD) and Aspect Category Sentiment Classification (ACSC).

• python 3.6
• pytorch 1.3.0
• allennlp 0.9.0

• SemEval-2014 Task 4
  • SemEval-2014-Task-4-LAPT
  • SemEval-2014-Task-4-REST
• 2018-aaai-Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis
  • SemEval-2014-Task-4-REST-DevSplits
• 2018-acl-Aspect Based Sentiment Analysis with Gated Convolutional Networks
  • SemEval-2014-Task-4-REST-Hard
  • SemEval-141516-LARGE-REST-HARD
• SemEval-2015 Task 12
  • SemEval-2015-Task-12-LAPT
  • SemEval-2015-Task-12-REST
  • SemEval-2015-Task-12-HOTEL
• SemEval-2016 Task 5
  • SemEval-2016-Task-5-CH-CAME-SB1
  • SemEval-2016-Task-5-CH-PHNS-SB1
  • SemEval-2016-Task-5-LAPT-SB1
  • SemEval-2016-Task-5-LAPT-SB2
  • SemEval-2016-Task-5-REST-SB1
  • SemEval-2016-Task-5-REST-SB2
• 2019-emnlp-A Challenge Dataset and Effective Models for Aspect Based Sentiment Analysis
  • MAMSACSA
  • MAMSATSA

• ae-lstm2016-emnlp-Attention-based LSTM for Aspect-level Sentiment Classification
• at-lstm2016-emnlp-Attention-based LSTM for Aspect-level Sentiment Classification
• atae-lstm2016-emnlp-Attention-based LSTM for Aspect-level Sentiment Classification
• Heat2017-CIKM-Aspect-level Sentiment Classification with HEAT (HiErarchical ATtention) Network

sh scripts/run.sh acsa/acac_pytorch/acsc_bootstrap.py --model_name Heat --current_dataset SemEval-2014-Task-4-REST-DevSplits --embedding_filepath glove.840B.300d.txt

sh scripts/run.sh acsa/acac_pytorch/acsc_bootstrap.py --model_name Heat --current_dataset SemEval-2014-Task-4-REST-DevSplits --embedding_filepath glove.840B.300d.txt --train False --visualize_attention True

Suggestions about adding papers are welcomed!

• 2016-emnlp-A Hierarchical Model of Reviews for Aspect-based Sentiment Analysispaper
• 2016-emnlp-Attention-based LSTM for Aspect-level Sentiment Classificationpaper
• 2017-CIKM-Aspect-level Sentiment Classification with HEAT (HiErarchical ATtention) Networkpaper
• 2018-aaai-Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysispaper
• 2018-acl-Aspect Based Sentiment Analysis with Gated Convolutional Networkspaper
• 2019-AAAI-A Human-Like Semantic Cognition Network for Aspect-Level Sentiment Classificationpaper
• 2019-conll-Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysispaper
• 2019-emnlp-A Challenge Dataset and Effective Models for Aspect Based Sentiment Analysispaper
• 2019-emnlp-A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysispaper
• 2019-ijcai-Earlier Attention Aspect-Aware LSTM for Aspect Sentiment Analysispaper
• 2019-naacl-Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentencepaper
• 2019-tkdd-Aspect Aware Learning for Aspect Category Sentiment Analysispaper
• 2020-nlpcc-Sentence Constituent-Aware Aspect-Category Sentiment Analysis with Graph Attention Networkspapercode
• 2020-emnlp-Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysispapercode
• 2021-naacl-ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Predictionpapercode
• 2021-emnlp-Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledgepapercode
• 2021-emnlp-Solving Aspect Category Sentiment Analysis as a Text Generation Taskpapercode

• 2017-wsdm-Deep Memory Networks for Attitude Identificationpaper
• 2018-emnlp-Joint Aspect and Polarity Classification for Adpect-based Sentiment Analysis with End-to-End Neural Networkspapercode
• 2019-www-Aspect-level Sentiment Analysis using AS-Capsulespapercode
• 2019-emnlp-CAN Constrained Attention Networks for Multi-Aspect Sentiment Analysispaper
• 2020-ccl-A Joint Model for Aspect-Category Sentiment Analysis with SharedSentiment Prediction Layerpapercode

• songyouwei/ABSA-PyTorch
• ZhengZixiang/ABSAPapers
• jiangqn/Aspect-Based-Sentiment-Analysis

Feel free to contribute!

You can raise an issue or submit a pull request, whichever is more convenient for you.

MIT License