{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T23:11:28Z","timestamp":1768345888926,"version":"3.49.0"},"reference-count":69,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376262"],"award-info":[{"award-number":["62376262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0902100"],"award-info":[{"award-number":["2022YFF0902100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Program","doi-asserted-by":"publisher","award":["KQTD20190929172835662"],"award-info":[{"award-number":["KQTD20190929172835662"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019443","name":"Shenzhen Research Foundation","doi-asserted-by":"publisher","award":["2021YFF1200100"],"award-info":[{"award-number":["2021YFF1200100"]}],"id":[{"id":"10.13039\/501100019443","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019443","name":"Shenzhen Research Foundation","doi-asserted-by":"publisher","award":["2021YFF1200104"],"award-info":[{"award-number":["2021YFF1200104"]}],"id":[{"id":"10.13039\/501100019443","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019443","name":"Shenzhen Research Foundation","doi-asserted-by":"publisher","award":["JCYJ20200109113441941"],"award-info":[{"award-number":["JCYJ20200109113441941"]}],"id":[{"id":"10.13039\/501100019443","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019443","name":"Shenzhen Research Foundation","doi-asserted-by":"publisher","award":["JCYJ20210324115614039"],"award-info":[{"award-number":["JCYJ20210324115614039"]}],"id":[{"id":"10.13039\/501100019443","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1016\/j.knosys.2023.111302","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T19:42:17Z","timestamp":1702928537000},"page":"111302","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":8,"special_numbering":"C","title":["Contrastive variational information bottleneck for aspect-based sentiment analysis"],"prefix":"10.1016","volume":"284","author":[{"given":"Mingshan","family":"Chang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7345-5071","authenticated-orcid":false,"given":"Min","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Qingshan","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Ruifeng","family":"Xu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2023.111302_b1","doi-asserted-by":"crossref","unstructured":"S. Negi, P. Buitelaar, INSIGHT Galway: Syntactic and Lexical Features for Aspect Based Sentiment Analysis, in: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), 2014, pp. 346\u2013350.","DOI":"10.3115\/v1\/S14-2058"},{"key":"10.1016\/j.knosys.2023.111302_b2","doi-asserted-by":"crossref","unstructured":"V. Pekar, N. Afzal, B. Bohnet, Ubham: Lexical resources and dependency parsing for aspect-based sentiment analysis, in: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), 2014, pp. 683\u2013687.","DOI":"10.3115\/v1\/S14-2122"},{"key":"10.1016\/j.knosys.2023.111302_b3","series-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","first-page":"606","article-title":"Attention-based LSTM for aspect-level sentiment classification","author":"Wang","year":"2016"},{"key":"10.1016\/j.knosys.2023.111302_b4","series-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","first-page":"214","article-title":"Aspect level sentiment classification with deep memory network","author":"Tang","year":"2016"},{"issue":"1","key":"10.1016\/j.knosys.2023.111302_b5","article-title":"Attention based LSTM for target dependent sentiment classification","volume":"31","author":"Yang","year":"2017","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2023.111302_b6","series-title":"Proceedings of the 26th International Joint Conference on Artificial Intelligence","first-page":"4068","article-title":"Interactive attention networks for aspect-level sentiment classification","author":"Ma","year":"2017"},{"key":"10.1016\/j.knosys.2023.111302_b7","series-title":"Proceedings of the 27th International Conference on Computational Linguistics","first-page":"1121","article-title":"Effective attention modeling for aspect-level sentiment classification","author":"He","year":"2018"},{"key":"10.1016\/j.knosys.2023.111302_b8","series-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","first-page":"3433","article-title":"Multi-grained attention network for aspect-level sentiment classification","author":"Fan","year":"2018"},{"key":"10.1016\/j.knosys.2023.111302_b9","series-title":"Proceedings of the 22nd Conference on Computational Natural Language Learning","first-page":"181","article-title":"Hierarchical attention based position-aware network for aspect-level sentiment analysis","author":"Li","year":"2018"},{"key":"10.1016\/j.knosys.2023.111302_b10","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","first-page":"5469","article-title":"Syntax-aware aspect level sentiment classification with graph attention networks","author":"Huang","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b11","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","first-page":"4568","article-title":"Aspect-based sentiment classification with aspect-specific graph convolutional networks","author":"Zhang","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b12","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","first-page":"5679","article-title":"Aspect-level sentiment analysis via convolution over dependency tree","author":"Sun","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b13","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"3229","article-title":"Relational graph attention network for aspect-based sentiment analysis","author":"Wang","year":"2020"},{"key":"10.1016\/j.knosys.2023.111302_b14","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"2910","article-title":"Aspect-based sentiment analysis with type-aware graph convolutional networks and layer ensemble","author":"Tian","year":"2021"},{"key":"10.1016\/j.knosys.2023.111302_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107736","article-title":"Phrase dependency relational graph attention network for aspect-based sentiment analysis","volume":"236","author":"Wu","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2023.111302_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107643","article-title":"Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks","volume":"235","author":"Liang","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2023.111302_b17","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b18","series-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b19","series-title":"Attentional encoder network for targeted sentiment classification","author":"Song","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b20","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","first-page":"6280","article-title":"A challenge dataset and effective models for aspect-based sentiment analysis","author":"Jiang","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b21","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"1816","article-title":"Does syntax matter? A strong baseline for aspect-based sentiment analysis with roBERTa","author":"Dai","year":"2021"},{"key":"10.1016\/j.knosys.2023.111302_b22","series-title":"Findings of the Association for Computational Linguistics: ACL 2022","first-page":"3599","article-title":"Incorporating dynamic semantics into pre-trained language model for aspect-based sentiment analysis","author":"Zhang","year":"2022"},{"key":"10.1016\/j.knosys.2023.111302_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109511","article-title":"ASK-roberta: A pretraining model for aspect-based sentiment classification via sentiment knowledge mining","volume":"253","author":"You","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2023.111302_b24","first-page":"1","article-title":"A survey on aspect-based sentiment analysis: Tasks, methods, and challenges","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2023.111302_b25","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"3594","article-title":"Tasty Burgers, soggy fries: Probing aspect robustness in aspect-based sentiment analysis","author":"Xing","year":"2020"},{"key":"10.1016\/j.knosys.2023.111302_b26","series-title":"The information bottleneck method","author":"Tishby","year":"2000"},{"issue":"1","key":"10.1016\/j.knosys.2023.111302_b27","article-title":"Learning latent opinions for aspect-level sentiment classification","volume":"32","author":"Wang","year":"2018","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2023.111302_b28","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"6319","article-title":"Dual graph convolutional networks for aspect-based sentiment analysis","author":"Li","year":"2021"},{"key":"10.1016\/j.knosys.2023.111302_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109840","article-title":"Sentiment interaction and multi-graph perception with graph convolutional networks for aspect-based sentiment analysis","volume":"256","author":"Lu","year":"2022","journal-title":"Knowl.-Based Syst."},{"issue":"16","key":"10.1016\/j.knosys.2023.111302_b30","first-page":"14094","article-title":"Context-guided BERT for targeted aspect-based sentiment analysis","volume":"35","author":"Wu","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2023.111302_b31","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"2324","article-title":"BERT post-training for review reading comprehension and aspect-based sentiment analysis","author":"Xu","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b32","series-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","first-page":"2021","article-title":"Adversarial examples for evaluating reading comprehension systems","author":"Jia","year":"2017"},{"key":"10.1016\/j.knosys.2023.111302_b33","series-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)","first-page":"107","article-title":"Annotation artifacts in natural language inference data","author":"Gururangan","year":"2018"},{"key":"10.1016\/j.knosys.2023.111302_b34","series-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","first-page":"5010","article-title":"How much reading does reading comprehension require? A critical investigation of popular benchmarks","author":"Kaushik","year":"2018"},{"key":"10.1016\/j.knosys.2023.111302_b35","series-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","first-page":"1975","article-title":"Behavior analysis of NLI models: Uncovering the influence of three factors on robustness","author":"Sanchez","year":"2018"},{"key":"10.1016\/j.knosys.2023.111302_b36","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"3428","article-title":"Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference","author":"McCoy","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b37","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"4658","article-title":"Probing neural network comprehension of natural language arguments","author":"Niven","year":"2019"},{"issue":"9","key":"10.1016\/j.knosys.2023.111302_b38","first-page":"10051","article-title":"On the impact of spurious correlation for out-of-distribution detection","volume":"36","author":"Ming","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2023.111302_b39","series-title":"Advances in Neural Information Processing Systems","first-page":"37199","article-title":"Is out-of-distribution detection learnable?","volume":"vol. 35","author":"Fang","year":"2022"},{"key":"10.1016\/j.knosys.2023.111302_b40","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"3122","article-title":"Learning bounds for open-set learning","volume":"vol. 139","author":"Fang","year":"2021"},{"key":"10.1016\/j.knosys.2023.111302_b41","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"4791","article-title":"HellaSwag: Can a machine really finish your sentence?","author":"Zellers","year":"2019"},{"key":"10.1016\/j.knosys.2023.111302_b42","series-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020","article-title":"Learning the difference that makes a difference with counterfactually-augmented data","author":"Kaushik","year":"2020"},{"issue":"9","key":"10.1016\/j.knosys.2023.111302_b43","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3474381","article-title":"WinoGrande: An adversarial winograd schema challenge at scale","volume":"64","author":"Sakaguchi","year":"2021","journal-title":"Commun. ACM"},{"key":"10.1016\/j.knosys.2023.111302_b44","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"4885","article-title":"Adversarial NLI: A new benchmark for natural language understanding","author":"Nie","year":"2020"},{"issue":"16","key":"10.1016\/j.knosys.2023.111302_b45","first-page":"14024","article-title":"Robustness to spurious correlations in text classification via automatically generated counterfactuals","volume":"35","author":"Wang","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2023.111302_b46","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2660","article-title":"Generating data to mitigate spurious correlations in natural language inference datasets","author":"Wu","year":"2022"},{"key":"10.1016\/j.knosys.2023.111302_b47","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"3031","article-title":"Learning to model and ignore dataset bias with mixed capacity ensembles","author":"Clark","year":"2020"},{"key":"10.1016\/j.knosys.2023.111302_b48","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"8706","article-title":"End-to-end bias mitigation by modelling biases in corpora","author":"Karimi Mahabadi","year":"2020"},{"key":"10.1016\/j.knosys.2023.111302_b49","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"8717","article-title":"Mind the trade-off: Debiasing NLU models without degrading the in-distribution performance","author":"Utama","year":"2020"},{"key":"10.1016\/j.knosys.2023.111302_b50","unstructured":"V. Sanh, T. Wolf, Y. Belinkov, A.M. Rush, Learning from others\u2019 mistakes: Avoiding dataset biases without modeling them, in: International Conference on Learning Representations, 2021, URL."},{"key":"10.1016\/j.knosys.2023.111302_b51","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"915","article-title":"Towards interpreting and mitigating shortcut learning behavior of NLU models","author":"Du","year":"2021"},{"issue":"9","key":"10.1016\/j.knosys.2023.111302_b52","first-page":"9521","article-title":"Towards debiasing DNN models from spurious feature influence","volume":"36","author":"Du","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2023.111302_b53","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"8281","article-title":"Avoiding the hypothesis-only bias in natural language inference via ensemble adversarial training","author":"Stacey","year":"2020"},{"key":"10.1016\/j.knosys.2023.111302_b54","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"3148","article-title":"Re-embedding difficult samples via mutual information constrained semantically oversampling for imbalanced text classification","author":"Tian","year":"2021"},{"key":"10.1016\/j.knosys.2023.111302_b55","unstructured":"C. Lovering, R. Jha, T. Linzen, E. Pavlick, Predicting Inductive Biases of Pre-Trained Models, in: International Conference on Learning Representations, 2021, URL."},{"key":"10.1016\/j.knosys.2023.111302_b56","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"12857","article-title":"Examining and combating spurious features under distribution shift","volume":"vol. 139","author":"Zhou","year":"2021"},{"key":"10.1016\/j.knosys.2023.111302_b57","unstructured":"R.K. Mahabadi, Y. Belinkov, J. Henderson, Variational Information Bottleneck for Effective Low-Resource Fine-Tuning, in: International Conference on Learning Representations, 2021, URL."},{"key":"10.1016\/j.knosys.2023.111302_b58","series-title":"Deep variational information bottleneck","author":"Alemi","year":"2016"},{"key":"10.1016\/j.knosys.2023.111302_b59","unstructured":"O. Fabius, J.R. van Amersfoort, D.P. Kingma, Variational Recurrent Auto-Encoders, in: ICLR (Workshop), 2015."},{"key":"10.1016\/j.knosys.2023.111302_b60","series-title":"Proceedings of the 35th International Conference on Machine Learning","first-page":"1135","article-title":"Compressing neural networks using the variational information bottleneck","volume":"vol. 80","author":"Dai","year":"2018"},{"key":"10.1016\/j.knosys.2023.111302_b61","doi-asserted-by":"crossref","unstructured":"A. Srivastava, O. Dutta, J. Gupta, S. Agarwal, P. AP, A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 2745\u20132754.","DOI":"10.1109\/WACV48630.2021.00279"},{"key":"10.1016\/j.knosys.2023.111302_b62","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume":"vol. 119","author":"Chen","year":"2020"},{"key":"10.1016\/j.knosys.2023.111302_b63","series-title":"Advances in Neural Information Processing Systems","first-page":"18661","article-title":"Supervised contrastive learning","volume":"vol. 33","author":"Khosla","year":"2020"},{"key":"10.1016\/j.knosys.2023.111302_b64","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"6894","article-title":"SimCSE: Simple contrastive learning of sentence embeddings","author":"Gao","year":"2021"},{"key":"10.1016\/j.knosys.2023.111302_b65","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"946","article-title":"Transformation networks for target-oriented sentiment classification","author":"Li","year":"2018"},{"key":"10.1016\/j.knosys.2023.111302_b66","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"3540","article-title":"Convolution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis","author":"Zhang","year":"2020"},{"key":"10.1016\/j.knosys.2023.111302_b67","series-title":"Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)","first-page":"27","article-title":"SemEval-2014 task 4: Aspect based sentiment analysis","author":"Pontiki","year":"2014"},{"key":"10.1016\/j.knosys.2023.111302_b68","series-title":"Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)","first-page":"486","article-title":"SemEval-2015 task 12: Aspect based sentiment analysis","author":"Pontiki","year":"2015"},{"key":"10.1016\/j.knosys.2023.111302_b69","series-title":"Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)","first-page":"19","article-title":"SemEval-2016 task 5: Aspect based sentiment analysis","author":"Pontiki","year":"2016"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512301050X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512301050X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:12:31Z","timestamp":1760595151000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512301050X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":69,"alternative-id":["S095070512301050X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2023.111302","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Contrastive variational information bottleneck for aspect-based sentiment analysis","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2023.111302","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"111302"}}