{"url":"/sota/aspect-based-sentiment-analysis-on-semeval","task":{"name":"Aspect-Based Sentiment Analysis (ABSA)","url":"/task/aspect-based-sentiment-analysis","note":null},"dataset":{"name":"SemEval-2014 Task-4","url":"/dataset/semeval-2014-task-4-sub-task-2"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Aspect-Based Sentiment Analysis (ABSA)** is a Natural Language Processing task that aims to identify and extract the sentiment of specific aspects or components of a product or service. ABSA typically involves a multi-step process that begins with identifying the aspects or features of the product or service that are being discussed in the text. This is followed by sentiment analysis, where the sentiment polarity (positive, negative, or neutral) is assigned to each aspect based on the context of the sentence or document. Finally, the results are aggregated to provide an overall sentiment for each aspect.\r\n\r\nAnd recent works propose more challenging ABSA tasks to predict sentiment triplets or quadruplets (Chen et al., 2022), the most influential of which are ASTE (Peng et al., 2020; Zhai et al., 2022), TASD (Wan et al., 2020), ASQP (Zhang et al., 2021a) and ACOS with an emphasis on the implicit aspects or opinions (Cai et al., 2020a).\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Source: [MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction](https://arxiv.org/abs/2305.12627) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Mean Acc (Restaurant + Laptop)","Restaurant (Acc)","Laptop (Acc)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean Acc (Restaurant + Laptop)":"higher","Restaurant (Acc)":"higher","Laptop (Acc)":"higher"}},"counts":{"rows":48,"rows_with_code":39,"rows_with_paper_page":48,"rows_dated":48,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"MT-ISA","metrics":{"Laptop (Acc)":"85.74","Mean Acc (Restaurant + Laptop)":"89.21","Restaurant (Acc)":"92.68"},"uses_additional_data":false,"paper_date":"2024-12-12","paper":"/paper/multi-task-learning-with-llms-for-implicit","paper_url":"https://arxiv.org/abs/2412.09046v1","paper_title":"Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"RVISA","metrics":{"Laptop (Acc)":"86.68","Mean Acc (Restaurant + Laptop)":"89.10","Restaurant (Acc)":"91.52"},"uses_additional_data":false,"paper_date":"2024-07-02","paper":"/paper/rvisa-reasoning-and-verification-for-implicit","paper_url":"https://arxiv.org/abs/2407.02340v1","paper_title":"RVISA: Reasoning and Verification for Implicit Sentiment Analysis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"LSA+DeBERTa-V3-Large","metrics":{"Laptop (Acc)":"86.21","Mean Acc (Restaurant + Laptop)":"88.27","Restaurant (Acc)":"90.33"},"uses_additional_data":false,"paper_date":"2021-10-16","paper":"/paper/back-to-reality-leveraging-pattern-driven","paper_url":"https://arxiv.org/abs/2110.08604v4","paper_title":"LSA: Modeling Aspect Sentiment Coherency via Local Sentiment Aggregation","code":"https://github.com/yangheng95/PyABSA/blob/release/demos/aspect_polarity_classification/run_fast_lsa_deberta_large.py","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"MaskedABSA","metrics":{"Laptop (Acc)":"86.24","Mean Acc (Restaurant + Laptop)":"86.95","Restaurant (Acc)":"87.65"},"uses_additional_data":false,"paper_date":"2024-09-02","paper":"/paper/masking-the-bias-from-echo-chambers-to-large","paper_url":"https://avesis.metu.edu.tr/yayin/7ffc1425-5d2a-486b-944a-2f8b39e7ca33/masking-the-bias-from-echo-chambers-to-large-scale-aspect-based-sentiment-analysis","paper_title":"Masking The Bias : From Echo Chambers to Large Scale Aspect-Based Sentiment Analysis","code":"https://github.com/tweetpie/masked-absa","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"LCF-ATEPC","metrics":{"Laptop (Acc)":"82.29","Mean Acc (Restaurant + Laptop)":"86.24","Restaurant (Acc)":"90.18"},"uses_additional_data":true,"paper_date":"2019-12-17","paper":"/paper/a-multi-task-learning-model-for-chinese","paper_url":"https://arxiv.org/abs/1912.07976v3","paper_title":"A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction","code":"https://github.com/yangheng95/LC-ABSA","n_code_links":6,"syntology":null},{"rank_in_archive_order":6,"model":"DPL-BERT","metrics":{"Laptop (Acc)":"81.96","Mean Acc (Restaurant + Laptop)":"85.75","Restaurant (Acc)":"89.54"},"uses_additional_data":true,"paper_date":"2022-03-14","paper":"/paper/towards-unifying-the-label-space-for-aspect","paper_url":"https://arxiv.org/abs/2203.07090v1","paper_title":"Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis","code":"https://github.com/yiming-zh/DPL","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"RoBERTa+MLP","metrics":{"Laptop (Acc)":"83.78","Mean Acc (Restaurant + Laptop)":"85.58","Restaurant (Acc)":"87.37"},"uses_additional_data":false,"paper_date":"2021-04-11","paper":"/paper/does-syntax-matter-a-strong-baseline-for","paper_url":"https://arxiv.org/abs/2104.04986v1","paper_title":"Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa","code":"https://github.com/ROGERDJQ/RoBERTaABSA","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"KaGRMN-DSG","metrics":{"Laptop (Acc)":"81.87","Mean Acc (Restaurant + Laptop)":"84.61","Restaurant (Acc)":"87.35"},"uses_additional_data":false,"paper_date":"2021-08-05","paper":"/paper/understand-me-if-you-refer-to-aspect","paper_url":"https://arxiv.org/abs/2108.02352v3","paper_title":"Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network","code":"https://github.com/XingBowen714/KaGRMN-DSG_ABSA","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"YORO","metrics":{"Laptop (Acc)":"81.82","Mean Acc (Restaurant + Laptop)":"84.48","Restaurant (Acc)":"87.14"},"uses_additional_data":false,"paper_date":"2024-03-24","paper":"/paper/you-only-read-once-constituency-oriented","paper_url":"https://ojs.aaai.org/index.php/AAAI/article/view/29945","paper_title":"You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification","code":"https://github.com/gdufsnlp/YORO","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"BERT-ADA","metrics":{"Laptop (Acc)":"80.23","Mean Acc (Restaurant + Laptop)":"84.06","Restaurant (Acc)":"87.89"},"uses_additional_data":true,"paper_date":"2019-08-30","paper":"/paper/adapt-or-get-left-behind-domain-adaptation","paper_url":"https://arxiv.org/abs/1908.11860v2","paper_title":"Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification","code":"https://github.com/yangheng95/LC-ABSA","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"RGAT+","metrics":{"Laptop (Acc)":"81.25","Mean Acc (Restaurant + Laptop)":"83.92","Restaurant (Acc)":"86.59"},"uses_additional_data":false,"paper_date":"2020-02-22","paper":"/paper/exploiting-typed-syntactic-dependencies-for","paper_url":"https://arxiv.org/abs/2002.09685v3","paper_title":"Investigating Typed Syntactic Dependencies for Targeted Sentiment Classification Using Graph Attention Neural Network","code":"https://github.com/muyeby/RGAT-ABSA","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"PH-SUM","metrics":{"Laptop (Acc)":"79.55","Mean Acc (Restaurant + Laptop)":"82.96","Restaurant (Acc)":"86.37"},"uses_additional_data":false,"paper_date":"2020-10-22","paper":"/paper/improving-bert-performance-for-aspect-based","paper_url":"https://arxiv.org/abs/2010.11731v2","paper_title":"Improving BERT Performance for Aspect-Based Sentiment Analysis","code":"https://github.com/IMPLabUniPr/BERT-for-ABSA","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"BAT","metrics":{"Laptop (Acc)":"79.35","Mean Acc (Restaurant + Laptop)":"82.69","Restaurant (Acc)":"86.03"},"uses_additional_data":false,"paper_date":"2020-01-30","paper":"/paper/adversarial-training-for-aspect-based","paper_url":"https://arxiv.org/abs/2001.11316v4","paper_title":"Adversarial Training for Aspect-Based Sentiment Analysis with BERT","code":"https://github.com/IMPLabUniPr/Adversarial-Training-for-ABSA","n_code_links":4,"syntology":null},{"rank_in_archive_order":14,"model":"SDGCN-BERT","metrics":{"Laptop (Acc)":"81.35","Mean Acc (Restaurant + Laptop)":"82.46","Restaurant (Acc)":"83.57"},"uses_additional_data":false,"paper_date":"2019-06-11","paper":"/paper/modeling-sentiment-dependencies-with-graph","paper_url":"https://arxiv.org/abs/1906.04501v1","paper_title":"Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification","code":"https://github.com/Pinlong-Zhao/SDGCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"BERT-SPC","metrics":{"Laptop (Acc)":"78.99","Mean Acc (Restaurant + Laptop)":"81.73","Restaurant (Acc)":"84.46"},"uses_additional_data":false,"paper_date":"2019-02-25","paper":"/paper/attentional-encoder-network-for-targeted","paper_url":"http://arxiv.org/abs/1902.09314v2","paper_title":"Attentional Encoder Network for Targeted Sentiment Classification","code":"https://github.com/songyouwei/ABSA-PyTorch","n_code_links":5,"syntology":null},{"rank_in_archive_order":16,"model":"AEN-BERT","metrics":{"Laptop (Acc)":"79.93","Mean Acc (Restaurant + Laptop)":"81.53","Restaurant (Acc)":"83.12"},"uses_additional_data":false,"paper_date":"2019-02-25","paper":"/paper/attentional-encoder-network-for-targeted","paper_url":"http://arxiv.org/abs/1902.09314v2","paper_title":"Attentional Encoder Network for Targeted Sentiment Classification","code":"https://github.com/songyouwei/ABSA-PyTorch","n_code_links":5,"syntology":null},{"rank_in_archive_order":17,"model":"BERT-PT","metrics":{"Laptop (Acc)":"78.07","Mean Acc (Restaurant + Laptop)":"81.51","Restaurant (Acc)":"84.95"},"uses_additional_data":true,"paper_date":"2019-04-03","paper":"/paper/bert-post-training-for-review-reading","paper_url":"https://arxiv.org/abs/1904.02232v2","paper_title":"BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis","code":"https://github.com/howardhsu/BERT-for-RRC-ABSA","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"InstructABSA","metrics":{"Laptop (Acc)":"80.56","Mean Acc (Restaurant + Laptop)":"81.5","Restaurant (Acc)":"82.44"},"uses_additional_data":false,"paper_date":"2023-02-16","paper":"/paper/instructabsa-instruction-learning-for-aspect","paper_url":"https://arxiv.org/abs/2302.08624v6","paper_title":"InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis","code":"https://github.com/kevinscaria/instructabsa","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"MCRF-SA","metrics":{"Laptop (Acc)":"77.64","Mean Acc (Restaurant + Laptop)":"80.25","Restaurant (Acc)":"82.86"},"uses_additional_data":false,"paper_date":"2020-10-06","paper":"/paper/aspect-sentiment-classification-with-aspect","paper_url":"https://arxiv.org/abs/2010.02696v2","paper_title":"Aspect Based Sentiment Analysis with Aspect-Specific Opinion Spans","code":"https://github.com/xuuuluuu/Aspect-Sentiment-Classification","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"HAPN","metrics":{"Laptop (Acc)":"77.27","Mean Acc (Restaurant + Laptop)":"79.75","Restaurant (Acc)":"82.23"},"uses_additional_data":false,"paper_date":"2018-10-01","paper":"/paper/hierarchical-attention-based-position-aware","paper_url":"https://aclanthology.org/K18-1018","paper_title":"Hierarchical Attention Based Position-Aware Network for Aspect-Level Sentiment Analysis","code":"https://github.com/DUT-LiuYang/Aspect-Sentiment-Analysis","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"IMN","metrics":{"Laptop (Acc)":"75.36","Mean Acc (Restaurant + Laptop)":"79.63","Restaurant (Acc)":"83.89"},"uses_additional_data":false,"paper_date":"2019-06-17","paper":"/paper/an-interactive-multi-task-learning-network","paper_url":"https://arxiv.org/abs/1906.06906v1","paper_title":"An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis","code":"https://github.com/lixin4ever/BERT-E2E-ABSA","n_code_links":3,"syntology":null},{"rank_in_archive_order":22,"model":"TNet-ATT(+AS)","metrics":{"Laptop (Acc)":"77.62","Mean Acc (Restaurant + Laptop)":"79.58","Restaurant (Acc)":"81.53"},"uses_additional_data":false,"paper_date":"2019-06-04","paper":"/paper/progressive-self-supervised-attention","paper_url":"https://arxiv.org/abs/1906.01213v3","paper_title":"Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis","code":"https://github.com/DeepLearnXMU/PSSAttention","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"MGAN","metrics":{"Laptop (Acc)":"76.21","Mean Acc (Restaurant + Laptop)":"78.85","Restaurant (Acc)":"81.49"},"uses_additional_data":false,"paper_date":"2018-11-16","paper":"/paper/exploiting-coarse-to-fine-task-transfer-for","paper_url":"http://arxiv.org/abs/1811.10999v1","paper_title":"Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification","code":"https://github.com/hsqmlzno1/MGAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"TNet-LF","metrics":{"Laptop (Acc)":"76.01","Mean Acc (Restaurant + Laptop)":"78.4","Restaurant (Acc)":"80.79"},"uses_additional_data":false,"paper_date":"2018-05-03","paper":"/paper/transformation-networks-for-target-oriented","paper_url":"http://arxiv.org/abs/1805.01086v1","paper_title":"Transformation Networks for Target-Oriented Sentiment Classification","code":"https://github.com/lixin4ever/TNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":25,"model":"SA-LSTM-P","metrics":{"Laptop (Acc)":"75.1","Mean Acc (Restaurant + Laptop)":"78.35","Restaurant (Acc)":"81.6"},"uses_additional_data":false,"paper_date":"2018-04-01","paper":"/paper/learning-latent-opinions-for-aspect-level","paper_url":"https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17327","paper_title":"Learning Latent Opinions for Aspect-Level Sentiment Classification","code":"https://github.com/berlino/SA-Sent","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"MGAN","metrics":{"Laptop (Acc)":"75.39","Mean Acc (Restaurant + Laptop)":"78.32","Restaurant (Acc)":"81.25"},"uses_additional_data":false,"paper_date":"2018-10-01","paper":"/paper/multi-grained-attention-network-for-aspect","paper_url":"https://aclanthology.org/D18-1380","paper_title":"Multi-grained Attention Network for Aspect-Level Sentiment Classification","code":"https://github.com/mindspore-courses/ABSA-MindSpore","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"LCR-Rot","metrics":{"Laptop (Acc)":"75.24","Mean Acc (Restaurant + Laptop)":"78.29","Restaurant (Acc)":"81.34"},"uses_additional_data":false,"paper_date":"2018-02-03","paper":"/paper/left-center-right-separated-neural-network","paper_url":"http://arxiv.org/abs/1802.00892v1","paper_title":"Left-Center-Right Separated Neural Network for Aspect-based Sentiment Analysis with Rotatory Attention","code":"https://github.com/NUSTM/ABSC","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"BILSTM-ATT-G (TSSVAE)","metrics":{"Laptop (Acc)":"75.34","Mean Acc (Restaurant + Laptop)":"78.22","Restaurant (Acc)":"81.10"},"uses_additional_data":false,"paper_date":"2018-10-24","paper":"/paper/semi-supervised-target-level-sentiment","paper_url":"https://arxiv.org/abs/1810.10437v3","paper_title":"Variational Semi-supervised Aspect-term Sentiment Analysis via Transformer","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"BBLSTM-SL","metrics":{"Laptop (Acc)":"74.9","Mean Acc (Restaurant + Laptop)":"78.1","Restaurant (Acc)":"81.3"},"uses_additional_data":false,"paper_date":"2018-05-01","paper":"/paper/aspect-based-sentiment-analysis-using-bitmask","paper_url":"https://aaai.org/ocs/index.php/FLAIRS/FLAIRS18/paper/view/17646","paper_title":"Aspect-Based Sentiment Analysis Using Bitmask Bidirectional Long Short Term Memory Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"AOA","metrics":{"Laptop (Acc)":"74.5","Mean Acc (Restaurant + Laptop)":"77.85","Restaurant (Acc)":"81.20"},"uses_additional_data":false,"paper_date":"2018-04-18","paper":"/paper/aspect-level-sentiment-classification-with","paper_url":"http://arxiv.org/abs/1804.06536v1","paper_title":"Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks","code":"https://github.com/songyouwei/ABSA-PyTorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":31,"model":"PBAN","metrics":{"Laptop (Acc)":"74.12","Mean Acc (Restaurant + Laptop)":"77.64","Restaurant (Acc)":"81.16"},"uses_additional_data":false,"paper_date":"2018-08-01","paper":"/paper/a-position-aware-bidirectional-attention","paper_url":"https://aclanthology.org/C18-1066","paper_title":"A Position-aware Bidirectional Attention Network for Aspect-level Sentiment Analysis","code":"https://github.com/hiyouga/PBAN-PyTorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"RAM","metrics":{"Laptop (Acc)":"74.49","Mean Acc (Restaurant + Laptop)":"77.36","Restaurant (Acc)":"80.23"},"uses_additional_data":false,"paper_date":"2017-09-01","paper":"/paper/recurrent-attention-network-on-memory-for","paper_url":"https://aclanthology.org/D17-1047","paper_title":"Recurrent Attention Network on Memory for Aspect Sentiment Analysis","code":"https://github.com/songyouwei/ABSA-PyTorch","n_code_links":3,"syntology":null},{"rank_in_archive_order":33,"model":"AEN-GloVe","metrics":{"Laptop (Acc)":"73.51","Mean Acc (Restaurant + Laptop)":"77.25","Restaurant (Acc)":"80.98"},"uses_additional_data":false,"paper_date":"2019-02-25","paper":"/paper/attentional-encoder-network-for-targeted","paper_url":"http://arxiv.org/abs/1902.09314v2","paper_title":"Attentional Encoder Network for Targeted Sentiment Classification","code":"https://github.com/songyouwei/ABSA-PyTorch","n_code_links":5,"syntology":null},{"rank_in_archive_order":34,"model":"IARM","metrics":{"Laptop (Acc)":"73.8","Mean Acc (Restaurant + Laptop)":"77.02","Restaurant (Acc)":"80.0"},"uses_additional_data":false,"paper_date":"2018-10-01","paper":"/paper/iarm-inter-aspect-relation-modeling-with","paper_url":"https://aclanthology.org/D18-1377","paper_title":"IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis","code":"https://github.com/senticnet/IARM","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"MemNet","metrics":{"Laptop (Acc)":"72.21","Mean Acc (Restaurant + Laptop)":"76.58","Restaurant (Acc)":"80.95"},"uses_additional_data":false,"paper_date":"2016-05-28","paper":"/paper/aspect-level-sentiment-classification-with-1","paper_url":"http://arxiv.org/abs/1605.08900v2","paper_title":"Aspect Level Sentiment Classification with Deep Memory Network","code":"https://github.com/songyouwei/ABSA-PyTorch","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":36,"model":"LSTM+SynATT+TarRep","metrics":{"Laptop (Acc)":"71.94","Mean Acc (Restaurant + Laptop)":"76.29","Restaurant (Acc)":"80.63"},"uses_additional_data":false,"paper_date":"2018-08-01","paper":"/paper/effective-attention-modeling-for-aspect-level","paper_url":"https://aclanthology.org/C18-1096","paper_title":"Effective Attention Modeling for Aspect-Level Sentiment Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":37,"model":"IAN","metrics":{"Laptop (Acc)":"72.10","Mean Acc (Restaurant + Laptop)":"75.35","Restaurant (Acc)":"78.60"},"uses_additional_data":false,"paper_date":"2017-09-04","paper":"/paper/interactive-attention-networks-for-aspect","paper_url":"http://arxiv.org/abs/1709.00893v1","paper_title":"Interactive Attention Networks for Aspect-Level Sentiment Classification","code":"https://github.com/songyouwei/ABSA-PyTorch","n_code_links":5,"syntology":null},{"rank_in_archive_order":38,"model":"JCI (hops)","metrics":{"Laptop (Acc)":"71.79","Mean Acc (Restaurant + Laptop)":"75.29","Restaurant (Acc)":"78.79"},"uses_additional_data":false,"paper_date":"2018-07-01","paper":"/paper/target-sensitive-memory-networks-for-aspect","paper_url":"https://aclanthology.org/P18-1088","paper_title":"Target-Sensitive Memory Networks for Aspect Sentiment Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":39,"model":"PRET+MULT","metrics":{"Laptop (Acc)":"71.15","Mean Acc (Restaurant + Laptop)":"75.13","Restaurant (Acc)":"79.11"},"uses_additional_data":false,"paper_date":"2018-06-12","paper":"/paper/exploiting-document-knowledge-for-aspect","paper_url":"http://arxiv.org/abs/1806.04346v1","paper_title":"Exploiting Document Knowledge for Aspect-level Sentiment Classification","code":"https://github.com/ruidan/Aspect-level-sentiment","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"PF-CNN","metrics":{"Laptop (Acc)":"70.06","Mean Acc (Restaurant + Laptop)":"74.63","Restaurant (Acc)":"79.20"},"uses_additional_data":false,"paper_date":"2019-09-13","paper":"/paper/parameterized-convolutional-neural-networks-1","paper_url":"https://arxiv.org/abs/1909.06276v1","paper_title":"Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":41,"model":"NP (hops)","metrics":{"Laptop (Acc)":"72.43","Mean Acc (Restaurant + Laptop)":"74.08","Restaurant (Acc)":"75.73"},"uses_additional_data":false,"paper_date":"2018-07-01","paper":"/paper/target-sensitive-memory-networks-for-aspect","paper_url":"https://aclanthology.org/P18-1088","paper_title":"Target-Sensitive Memory Networks for Aspect Sentiment Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":42,"model":"ATAE-LSTM","metrics":{"Laptop (Acc)":"68.70","Mean Acc (Restaurant + Laptop)":"72.95","Restaurant (Acc)":"77.20"},"uses_additional_data":false,"paper_date":"2016-11-01","paper":"/paper/attention-based-lstm-for-aspect-level","paper_url":"https://aclanthology.org/D16-1058","paper_title":"Attention-based LSTM for Aspect-level Sentiment Classification","code":"https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/pytorch_alstm.py","n_code_links":8,"syntology":null},{"rank_in_archive_order":43,"model":"TD-LSTM","metrics":{"Laptop (Acc)":"68.13","Mean Acc (Restaurant + Laptop)":"71.88","Restaurant (Acc)":"75.63"},"uses_additional_data":false,"paper_date":"2015-12-03","paper":"/paper/effective-lstms-for-target-dependent","paper_url":"http://arxiv.org/abs/1512.01100v2","paper_title":"Effective LSTMs for Target-Dependent Sentiment Classification","code":"https://github.com/songyouwei/ABSA-PyTorch","n_code_links":10,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":44,"model":"BERT-IL Finetuned","metrics":{"Restaurant (Acc)":"86.20"},"uses_additional_data":false,"paper_date":"2020-11-23","paper":"/paper/does-bert-understand-sentiment-leveraging","paper_url":"https://arxiv.org/abs/2011.11673v1","paper_title":"Does BERT Understand Sentiment? Leveraging Comparisons Between Contextual and Non-Contextual Embeddings to Improve Aspect-Based Sentiment Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":45,"model":"ATLX-Ent","metrics":{"Restaurant (Acc)":"82.86"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/attention-and-lexicon-regularized-lstm-for","paper_url":"https://aclanthology.org/P19-2035","paper_title":"Attention and Lexicon Regularized LSTM for Aspect-based Sentiment Analysis","code":"https://github.com/LingxB/atlx","n_code_links":1,"syntology":null},{"rank_in_archive_order":46,"model":"ATLX","metrics":{"Restaurant (Acc)":"82.62"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/attention-and-lexicon-regularized-lstm-for","paper_url":"https://aclanthology.org/P19-2035","paper_title":"Attention and Lexicon Regularized LSTM for Aspect-based Sentiment Analysis","code":"https://github.com/LingxB/atlx","n_code_links":1,"syntology":null},{"rank_in_archive_order":47,"model":"TNet","metrics":{"Laptop (Acc)":"76.01","Restaurant (Acc)":"80.79"},"uses_additional_data":false,"paper_date":"2018-05-03","paper":"/paper/transformation-networks-for-target-oriented","paper_url":"http://arxiv.org/abs/1805.01086v1","paper_title":"Transformation Networks for Target-Oriented Sentiment Classification","code":"https://github.com/lixin4ever/TNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":48,"model":"ABSA-DeBERTa","metrics":{"Laptop (Acc)":"82,76","Mean Acc (Restaurant + Laptop)":"86,11","Restaurant (Acc)":"89,46"},"uses_additional_data":false,"paper_date":"2021-07-18","paper":"/paper/aspect-based-sentiment-analysis-using-bert","paper_url":"https://research.latinxinai.org/papers/icml/2021/pdf/paper_28.pdf","paper_title":"Aspect-based Sentiment Analysis using BERT with Disentangled Attention","code":"https://github.com/huberemanuel/ABSA-DeBERTa","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":5,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":8,"n_unverified":22,"n_samples":30,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":8,"n_unverified":22,"n_samples":30,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}