{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T21:18:45Z","timestamp":1762809525042},"reference-count":65,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T00:00:00Z","timestamp":1706832000000},"content-version":"vor","delay-in-days":32,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Few-shot Aspect Category Sentiment Analysis (ACSA) is a crucial task for aspect-based sentiment analysis, which aims to detect sentiment polarity for a given aspect category in a sentence with limited data. However, few-shot learning methods focus on distance metrics between the query and support sets to classify queries, heavily relying on aspect distributions in the embedding space. Thus, they suffer from overlapping distributions of aspect embeddings caused by irrelevant sentiment noise among sentences with multiple sentiment aspects, leading to misclassifications. To solve the above issues, we propose a metric-free method for few-shot ACSA, which models the associated relations among the aspects of support and query sentences by Dual Relations Propagation (DRP), addressing the passive effect of overlapping distributions. Specifically, DRP uses the dual relations (similarity and diversity) among the aspects of support and query sentences to explore intra-cluster commonality and inter-cluster uniqueness for alleviating sentiment noise and enhancing aspect features. Additionally, the dual relations are transformed from support-query to class-query to promote query inference by learning class knowledge. Experiments show that we achieve convincing performance on few-shot ACSA, especially an average improvement of 2.93% accuracy and 2.10% F1 score in the 3-way 1-shot setting.<\/jats:p>","DOI":"10.1162\/tacl_a_00635","type":"journal-article","created":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T23:51:20Z","timestamp":1706917880000},"page":"100-119","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":3,"title":["Metric-Free Learning Network with Dual Relations Propagation for Few-Shot Aspect Category Sentiment Analysis"],"prefix":"10.1162","volume":"12","author":[{"given":"Shiman","family":"Zhao","sequence":"first","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University"},{"name":"Beijing, China Research Center for Computational Social Science, Peking University, Institute of Computational Social Science, Peking University (Qingdao). shimanzhao@stu.pku.edu.cn"}]},{"given":"Yutao","family":"Xie","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University"},{"name":"Beijing, China Research Center for Computational Social Science, Peking University, Institute of Computational Social Science, Peking University (Qingdao). yutao_xie@stu.pku.edu.cn"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University"},{"name":"Beijing, China Research Center for Computational Social Science, Peking University, Institute of Computational Social Science, Peking University (Qingdao). pekingchenwei@pku.edu.cn"}]},{"given":"Tengjiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University"},{"name":"Beijing, China Research Center for Computational Social Science, Peking University, Institute of Computational Social Science, Peking University (Qingdao). tjwang@pku.edu.cn"}]},{"given":"Jiahui","family":"Yao","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University"},{"name":"Beijing, China Research Center for Computational Social Science, Peking University, Institute of Computational Social Science, Peking University (Qingdao). isssyaojh@pku.edu.cn"}]},{"given":"Jiabin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University"},{"name":"Beijing, China Research Center for Computational Social Science, Peking University, Institute of Computational Social Science, Peking University (Qingdao). jiabinzheng@pku.edu.cn"}]}],"member":"281","published-online":{"date-parts":[[2024,1,31]]},"reference":[{"key":"2024020223510462100_bib1","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1016\/j.neucom.2021.11.064","article-title":"A deep learning based trust-and tag-aware recommender system","volume":"488","author":"Ahmadian","year":"2022","journal-title":"Neurocomputing"},{"key":"2024020223510462100_bib2","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1007\/978-3-031-19821-2_26","article-title":"Masked Siamese networks for label-efficient learning","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Assran","year":"2022"},{"key":"2024020223510462100_bib3","doi-asserted-by":"publisher","first-page":"340","DOI":"10.18653\/v1\/2021.acl-long.29","article-title":"Aspect-category-opinion-sentiment quadruple extraction with implicit aspects and opinions","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","author":"Cai","year":"2021"},{"key":"2024020223510462100_bib4","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/3340531.3412003","article-title":"Senticnet 6: Ensemble application of symbolic and subsymbolic AI for sentiment analysis","volume-title":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","author":"Cambria","year":"2020"},{"key":"2024020223510462100_bib5","doi-asserted-by":"publisher","first-page":"2051","DOI":"10.18653\/v1\/2022.acl-long.145","article-title":"Discrete opinion tree induction for aspect-based sentiment analysis","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","author":"Chen","year":"2022"},{"key":"2024020223510462100_bib6","doi-asserted-by":"publisher","first-page":"10492","DOI":"10.1609\/aaai.v36i10.21292","article-title":"Contrastnet: A contrastive learning framework for few-shot text classification","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Chen","year":"2022"},{"key":"2024020223510462100_bib7","doi-asserted-by":"publisher","first-page":"7612","DOI":"10.1109\/ICASSP43922.2022.9747843","article-title":"Joint multiple intent detection and slot filling via self-distillation","volume-title":"ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Chen","year":"2022"},{"key":"2024020223510462100_bib8","doi-asserted-by":"publisher","first-page":"7409","DOI":"10.18653\/v1\/2023.acl-long.409","article-title":"Consistent prototype learning for few-shot continual relation extraction","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","author":"Chen","year":"2023"},{"issue":"4","key":"2024020223510462100_bib9","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1109\/TSC.2020.2964552","article-title":"Personalized recommendation system based on collaborative filtering for iot scenarios","volume":"13","author":"Cui","year":"2020","journal-title":"IEEE Transactions on Services Computing"},{"key":"2024020223510462100_bib10","doi-asserted-by":"publisher","first-page":"13773","DOI":"10.1609\/aaai.v34i10.7158","article-title":"When low resource NLP meets unsupervised language model: Meta-pretraining then meta-learning for few-shot text classification","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Deng","year":"2020"},{"key":"2024020223510462100_bib11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin","year":"2019"},{"key":"2024020223510462100_bib12","doi-asserted-by":"publisher","first-page":"2327","DOI":"10.5555\/2832415.2832572","article-title":"Deep learning for event-driven stock prediction","volume-title":"Proceedings of the 24th International Conference on Artificial IntelligenceJuly","author":"Ding","year":"2015"},{"key":"2024020223510462100_bib13","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1162\/tacl_a_00537","article-title":"Improving low-resource cross-lingual parsing with expected statistic regularization","volume":"11","author":"Effland","year":"2023","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2024020223510462100_bib14","doi-asserted-by":"publisher","first-page":"4261","DOI":"10.18653\/v1\/2023.acl-long.234","article-title":"MANNER: A variational memory-augmented model for cross domain few-shot named entity recognition","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","author":"Fang","year":"2023"},{"issue":"6","key":"2024020223510462100_bib15","doi-asserted-by":"publisher","first-page":"1725","DOI":"10.1109\/TCSS.2022.3178416","article-title":"The joint method of triple attention and novel loss function for entity relation extraction in small data-driven computational social systems","volume":"9","author":"Gao","year":"2022","journal-title":"IEEE Transactions on Computational Social Systems"},{"key":"2024020223510462100_bib16","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1109\/IALP.2017.8300611","article-title":"Implicit discourse relation identification based on tree structure neural network","volume-title":"2017 International Conference on Asian Language Processing (IALP)","author":"Geng","year":"2017"},{"key":"2024020223510462100_bib17","doi-asserted-by":"publisher","first-page":"3895","DOI":"10.18653\/v1\/D19-1403","article-title":"Induction networks for few-shot text classification","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","author":"Geng","year":"2019"},{"key":"2024020223510462100_bib18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.58","article-title":"A generative language model for few-shot aspect-based sentiment analysis","volume-title":"Findings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Hosseini-Asl","year":"2022"},{"key":"2024020223510462100_bib19","doi-asserted-by":"publisher","first-page":"13036","DOI":"10.1609\/aaai.v35i14.17541","article-title":"Few-shot learning for multi-label intent detection","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Hou","year":"2021"},{"key":"2024020223510462100_bib20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.495","article-title":"Multi-label few-shot learning for aspect category detection","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics","author":"Mengting","year":"2021"},{"key":"2024020223510462100_bib21","article-title":"Pushing the limits of simple pipelines for few-shot learning: External data and fine-tuning make a difference","author":"Shell Xu","year":"2022"},{"key":"2024020223510462100_bib22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00875","article-title":"Metasets: Meta-learning on point sets for generalizable representations","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Huang","year":"2021"},{"issue":"5","key":"2024020223510462100_bib23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3453154","article-title":"A survey on conversational recommender systems","volume":"54","author":"Jannach","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2024020223510462100_bib24","doi-asserted-by":"publisher","first-page":"6280","DOI":"10.18653\/v1\/D19-1654","article-title":"A challenge dataset and effective models for aspect-based sentiment analysis","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","author":"Jiang","year":"2019"},{"key":"2024020223510462100_bib25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.03090","article-title":"What would Elsa do? Freezing layers during transformer fine-tuning","author":"Lee","year":"2019","journal-title":"arXiv preprint arXiv:1911.03090v1"},{"key":"2024020223510462100_bib26","first-page":"10657","article-title":"Meta-learning with differentiable convex optimization","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lee","year":"2019"},{"key":"2024020223510462100_bib27","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1145\/3488560.3498404","article-title":"Unsupervised cross-domain adaptation for response selection using self-supervised and adversarial training","volume-title":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","author":"Li","year":"2022"},{"key":"2024020223510462100_bib28","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1145\/3511808.3557452","article-title":"SK2: Integrating implicit sentiment knowledge and explicit syntax knowledge for aspect-based sentiment analysis","volume-title":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","author":"Li","year":"2022"},{"key":"2024020223510462100_bib29","doi-asserted-by":"publisher","first-page":"15339","DOI":"10.48550\/arXiv.2305.05711","article-title":"CodeIE: Large code generation models are better few-shot information extractors","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","author":"Li","year":"2023"},{"key":"2024020223510462100_bib30","doi-asserted-by":"publisher","first-page":"6319","DOI":"10.18653\/v1\/2021.acl-long.494","article-title":"Dual graph convolutional networks for aspect-based sentiment analysis","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","author":"Li","year":"2021"},{"key":"2024020223510462100_bib31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jechem.2020.05.012","article-title":"Hollow feco-fecop@c nanocubes embedded in nitrogen-doped carbon nanocages for efficient overall water splitting","volume":"53","author":"Li","year":"2021","journal-title":"Journal of Energy Chemistry"},{"key":"2024020223510462100_bib32","doi-asserted-by":"publisher","first-page":"3550","DOI":"10.18653\/v1\/2020.emnlp-main.287","article-title":"Multi-instance multi-label learning networks for aspect-category sentiment analysis","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","author":"Li","year":"2020"},{"issue":"1","key":"2024020223510462100_bib33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3529954","article-title":"Few-shot aspect category sentiment analysis via meta-learning","volume":"41","author":"Liang","year":"2023","journal-title":"ACM Transactions on Information Systems"},{"key":"2024020223510462100_bib34","article-title":"Embedding refinement framework for targeted aspect-based sentiment analysis","author":"Liang","year":"2021","journal-title":"IEEE Transactions on Affective Computing"},{"key":"2024020223510462100_bib35","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1145\/3534678.3539340","article-title":"Label-enhanced prototypical network with contrastive learning for multi-label few-shot aspect category detection","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Liu","year":"2022"},{"key":"2024020223510462100_bib36","doi-asserted-by":"publisher","first-page":"106810","DOI":"10.1016\/j.knosys.2021.106810","article-title":"Co-attention networks based on aspect and context for aspect-level sentiment analysis","volume":"217","author":"Liu","year":"2021","journal-title":"Knowledge-Based Systems"},{"key":"2024020223510462100_bib37","first-page":"1291","article-title":"Automated rule selection for aspect extraction in opinion mining","volume-title":"Proceedings of International Joint Conference on Artificial Intelligence","author":"Liu","year":"2015"},{"key":"2024020223510462100_bib38","doi-asserted-by":"publisher","first-page":"14391","DOI":"10.1109\/CVPR52688.2022.01401","article-title":"Learning to affiliate: Mutual centralized learning for few-shot classification","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2022"},{"key":"2024020223510462100_bib39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.395","article-title":"Unified structure generation for universal information extraction","volume-title":"Proceedings of the Conference on Association for Computational Linguistics","author":"Yaojie","year":"2022"},{"key":"2024020223510462100_bib40","doi-asserted-by":"publisher","first-page":"15425","DOI":"10.1109\/CVPR46437.2021.01517","article-title":"Learning normal dynamics in videos with meta prototype network","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lv","year":"2021"},{"key":"2024020223510462100_bib41","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.18653\/v1\/2023.findings-acl.253","article-title":"Coarse-to-fine few-shot learning for named entity recognition","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Ma","year":"2023"},{"issue":"7","key":"2024020223510462100_bib42","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1109\/TMI.2022.3150682","article-title":"Self-supervised learning for few-shot medical image segmentation","volume":"41","author":"Ouyang","year":"2022","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"2024020223510462100_bib43","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"2024020223510462100_bib44","article-title":"Dynamic routing between capsules","volume":"30","author":"Sabour","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024020223510462100_bib45","doi-asserted-by":"publisher","first-page":"6311","DOI":"10.18653\/v1\/2021.emnlp-main.509","article-title":"Open aspect target sentiment classification with natural language prompts","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Seoh","year":"2021"},{"key":"2024020223510462100_bib46","doi-asserted-by":"publisher","first-page":"103477","DOI":"10.1016\/j.artint.2021.103477","article-title":"Enhanced aspect-based sentiment analysis models with progressive self-supervised attention learning","volume":"296","author":"Jinsong","year":"2021","journal-title":"Artificial Intelligence"},{"key":"2024020223510462100_bib47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.02955","article-title":"Zlpr: A novel loss for multi-label classification","author":"Jianlin","year":"2022","journal-title":"arXiv preprint arXiv:2208.02955v1"},{"key":"2024020223510462100_bib48","first-page":"380","article-title":"Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Sun","year":"2019"},{"key":"2024020223510462100_bib49","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1109\/CVPR.2018.00131","article-title":"Learning to compare: Relation network for few-shot learning","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sung","year":"2018"},{"key":"2024020223510462100_bib50","doi-asserted-by":"publisher","first-page":"8432","DOI":"10.1609\/aaai.v36i8.20819","article-title":"FedProto: Federated prototype learning across heterogeneous clients","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Tan","year":"2022"},{"key":"2024020223510462100_bib51","doi-asserted-by":"publisher","first-page":"2910","DOI":"10.18653\/v1\/2021.naacl-main.231","article-title":"Aspect-based sentiment analysis with type-aware graph convolutional networks and layer ensemble","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Tian","year":"2021"},{"key":"2024020223510462100_bib52","first-page":"2554","article-title":"Meta networks","volume-title":"International Conference on Machine Learning","author":"Tsendsuren","year":"2017"},{"issue":"9","key":"2024020223510462100_bib53","doi-asserted-by":"publisher","first-page":"5261","DOI":"10.1109\/TPAMI.2021.3078053","article-title":"Neural graph matching network: Learning lawler\u2019s quadratic assignment problem with extension to hypergraph and multiple-graph matching","volume":"44","author":"Wang","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2024020223510462100_bib54","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.neucom.2021.01.019","article-title":"Residual attention and other aspects module for aspect-based sentiment analysis","volume":"435","author":"Chao","year":"2021","journal-title":"Neurocomputing"},{"key":"2024020223510462100_bib55","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.10.091","article-title":"Exploring fine-grained syntactic information for aspect-based sentiment classification with dual graph neural networks","volume":"471","author":"Xiao","year":"2022","journal-title":"Neurocomputing"},{"key":"2024020223510462100_bib56","doi-asserted-by":"publisher","first-page":"9193","DOI":"10.18653\/v1\/2021.emnlp-main.724","article-title":"BERT4GCN: Using BERT intermediate layers to augment GCN for aspect-based sentiment classification","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Xiao","year":"2021"},{"key":"2024020223510462100_bib57","doi-asserted-by":"publisher","first-page":"2621","DOI":"10.18653\/v1\/2023.findings-acl.164","article-title":"Focusing, bridging and prompting for few-shot nested named entity recognition","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Yuanyuan","year":"2023"},{"key":"2024020223510462100_bib58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.07203","article-title":"Prototypical networks for multi-label learning","volume-title":"Proceedings of the International Conference Association for the Advancement of Artificial Intelligence","author":"Yang","year":"2020"},{"key":"2024020223510462100_bib59","doi-asserted-by":"publisher","first-page":"3179","DOI":"10.1609\/aaai.v36i3.20226","article-title":"Hybrid graph neural networks for few-shot learning","volume-title":"Proceedings of the AAAI conference on artificial intelligence","author":"Tianyuan","year":"2022"},{"key":"2024020223510462100_bib60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.12692","article-title":"MetaAdapt: Domain adaptive few-shot misinformation detection via meta learning","volume-title":"Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics","author":"Yue","year":"2023"},{"key":"2024020223510462100_bib61","doi-asserted-by":"publisher","first-page":"9014","DOI":"10.1609\/aaai.v36i8.20885","article-title":"MetaNODE: Prototype optimization as a neural ODE for few-shot learning","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Zhang","year":"2022"},{"key":"2024020223510462100_bib62","doi-asserted-by":"publisher","first-page":"3221","DOI":"10.48550\/arXiv.2005.07522","article-title":"Parallel data augmentation for formality style transfer","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Yi","year":"2020"},{"key":"2024020223510462100_bib63","doi-asserted-by":"publisher","first-page":"9127","DOI":"10.1609\/aaai.v36i8.20898","article-title":"ProtGNN: Towards self-explaining graph neural networks","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Zhang","year":"2022"},{"key":"2024020223510462100_bib64","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/589","article-title":"Learning few-shot sample-set operations for noisy multi-label aspect category detection","volume-title":"Proceedings of International Joint Conference on Artificial Intelligence","author":"Zhao","year":"2023"},{"key":"2024020223510462100_bib65","doi-asserted-by":"publisher","first-page":"5129","DOI":"10.18653\/v1\/2022.acl-long.352","article-title":"KNN-contrastive learning for out-of-domain intent classification","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","author":"Zhou","year":"2022"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00635\/2325695\/tacl_a_00635.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00635\/2325695\/tacl_a_00635.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T23:51:33Z","timestamp":1706917893000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00635\/119277\/Metric-Free-Learning-Network-with-Dual-Relations"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00635","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}