{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:34:59Z","timestamp":1785422099565,"version":"3.56.0"},"reference-count":69,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T00:00:00Z","timestamp":1689206400000},"content-version":"vor","delay-in-days":193,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Semi-supervised text classification-based paradigms (SSTC) typically employ the spirit of self-training. The key idea is to train a deep classifier on limited labeled texts and then iteratively predict the unlabeled texts as their pseudo-labels for further training. However, the performance is largely affected by the accuracy of pseudo-labels, which may not be significant in real-world scenarios. This paper presents a Rank-aware Negative Training (RNT) framework to address SSTC in learning with noisy label settings. To alleviate the noisy information, we adapt a reasoning with uncertainty-based approach to rank the unlabeled texts based on the evidential support received from the labeled texts. Moreover, we propose the use of negative training to train RNT based on the concept that \u201cthe input instance does not belong to the complementary label\u201d. A complementary label is randomly selected from all labels except the label on-target. Intuitively, the probability of a true label serving as a complementary label is low and thus provides less noisy information during the training, resulting in better performance on the test data. Finally, we evaluate the proposed solution on various text classification benchmark datasets. Our extensive experiments show that it consistently overcomes the state-of-the-art alternatives in most scenarios and achieves competitive performance in the others. The code of RNT is publicly available on GitHub.<\/jats:p>","DOI":"10.1162\/tacl_a_00574","type":"journal-article","created":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T16:42:03Z","timestamp":1689266523000},"page":"771-786","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":15,"title":["Rank-Aware Negative Training for Semi-Supervised Text Classification"],"prefix":"10.1162","volume":"11","author":[{"given":"Ahmed","family":"Murtadha","sequence":"first","affiliation":[{"name":"Zhuiyi Technology Co., Ltd. Shenzhen, Guangdong, China. a.murtadha@wezhuiyi.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengfeng","family":"Pan","sequence":"additional","affiliation":[{"name":"Zhuiyi Technology Co., Ltd. Shenzhen, Guangdong, China. nickpan@wezhuiyi.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Bo","sequence":"additional","affiliation":[{"name":"Zhuiyi Technology Co., Ltd. Shenzhen, Guangdong, China. brucewen@wezhuiyi.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlin","family":"Su","sequence":"additional","affiliation":[{"name":"Zhuiyi Technology Co., Ltd. Shenzhen, Guangdong, China. bojonesu@wezhuiyi.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinxin","family":"Cao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi\u2019an, Shaanxi, China. caoxinxin@mail.nwpu.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenze","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhuiyi Technology Co., Ltd. Shenzhen, Guangdong, China. wen@wezhuiyi.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunfeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhuiyi Technology Co., Ltd. Shenzhen, Guangdong, China. glenliu@wezhuiyi.com"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2023,7,12]]},"reference":[{"key":"2023071316415435300_bib1","doi-asserted-by":"publisher","first-page":"488","DOI":"10.18653\/v1\/2021.findings-acl.43","article-title":"DNN-driven gradual machine learning for aspect-term sentiment analysis","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics: ACL\/IJCNLP, Findings","author":"Ahmed","year":"2021"},{"key":"2023071316415435300_bib2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.11702","article-title":"BERT-ASC: Auxiliary-sentence construction for implicit aspect learning in sentiment analysis","volume":"abs\/2203.11702","author":"Ahmed","year":"2022","journal-title":"CoRR"},{"key":"2023071316415435300_bib3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN48605.2020.9207304","article-title":"Pseudo-labeling and confirmation bias in deep semi-supervised learning","volume-title":"Proceedings of the International Joint Conference on Neural Networks, IJCNN","author":"Arazo","year":"2020"},{"key":"2023071316415435300_bib4","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.1109\/ICPR56361.2022.9956388","article-title":"Learning from better supervision: Self-distillation for learning with noisy labels","volume-title":"Proceedings of the 26th International Conference on Pattern Recognition, ICPR","author":"Baek","year":"2022"},{"key":"2023071316415435300_bib5","article-title":"Synthetic and natural noise both break neural machine translation","volume-title":"Proceedings of the 6th International Conference on Learning Representations, ICLR","author":"Belinkov","year":"2018"},{"key":"2023071316415435300_bib6","first-page":"830","article-title":"Importance of semantic representation: Dataless classification","volume-title":"Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, AAAI","author":"Chang","year":"2008"},{"key":"2023071316415435300_bib7","doi-asserted-by":"publisher","first-page":"2147","DOI":"10.18653\/v1\/2020.acl-main.194","article-title":"MixText: Linguistically-informed interpolation of hidden space for semi-supervised text classification","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL","author":"Chen","year":"2020"},{"key":"2023071316415435300_bib8","doi-asserted-by":"publisher","first-page":"215","DOI":"10.18653\/v1\/D18-1020","article-title":"Variational sequential labelers for semi-supervised learning","volume-title":"Proceedings of the Empirical Methods in Natural Language Processing, EMNLP","author":"Chen","year":"2018"},{"key":"2023071316415435300_bib9","doi-asserted-by":"publisher","first-page":"452","DOI":"10.18653\/v1\/D17-1047","article-title":"Recurrent attention network on memory for aspect sentiment analysis","volume-title":"Proceedings of the Empirical Methods in Natural Language Processing, EMNLP 2017","author":"Chen","year":"2017"},{"key":"2023071316415435300_bib10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.08702","article-title":"Dual Contrastive learning: Text classification via label-aware data augmentation","author":"Chen","year":"2022","journal-title":"CoRR"},{"key":"2023071316415435300_bib11","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.18653\/v1\/E17-1104","article-title":"Very Deep Convolutional Networks for Text Classification","volume-title":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL","author":"Conneau","year":"2017"},{"key":"2023071316415435300_bib12","doi-asserted-by":"publisher","first-page":"657","DOI":"10.18653\/v1\/2020.findings-emnlp.58","article-title":"Revisiting pre-trained models for Chinese natural language processing","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: EMNLP, Findings","author":"Cui","year":"2020"},{"key":"2023071316415435300_bib13","doi-asserted-by":"publisher","first-page":"3504","DOI":"10.1109\/TASLP.2021.3124365","article-title":"Pre-training with whole word masking for Chinese BERT","volume":"29","author":"Cui","year":"2021","journal-title":"IEEE ACM Transactions on Audio, Speech, and Language Processing"},{"key":"2023071316415435300_bib14","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT","author":"Devlin","year":"2019"},{"key":"2023071316415435300_bib15","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1145\/1341531.1341561","article-title":"A holistic lexicon-based approach to opinion mining","volume-title":"Proceedings of the International Conference on Web Search and Web Data Mining, WSDM","author":"Ding","year":"2008"},{"issue":"2","key":"2023071316415435300_bib16","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","article-title":"A survey on semi-supervised learning","volume":"109","author":"van Engelen","year":"2020","journal-title":"Machine Learning"},{"key":"2023071316415435300_bib17","doi-asserted-by":"publisher","first-page":"5880","DOI":"10.18653\/v1\/P19-1590","article-title":"Variational pretraining for semi-supervised text classification","volume-title":"Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL","author":"Gururangan","year":"2019"},{"key":"2023071316415435300_bib18","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"Proceedings of the Neural Information Processing Systems","author":"Bo","year":"2018"},{"issue":"2","key":"2023071316415435300_bib19","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1109\/TKDE.2018.2883532","article-title":"r-HUMO: A risk-aware human-machine cooperation framework for entity resolution with quality guarantees","volume":"32","author":"Hou","year":"2020","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2023071316415435300_bib20","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1145\/1014052.1014073","article-title":"Mining and summarizing customer reviews","volume-title":"Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Minqing","year":"2004"},{"key":"2023071316415435300_bib21","doi-asserted-by":"publisher","first-page":"562","DOI":"10.18653\/v1\/P17-1052","article-title":"Deep pyramid convolutional neural networks for text categorization","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL","author":"Johnson","year":"2017"},{"key":"2023071316415435300_bib22","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/3437963.3441814","article-title":"Semi-supervised text classification via self-pretraining","volume-title":"Proceedings of the Fourteenth ACM International Conference on Web Search and Data Mining WSDM","author":"Karisani","year":"2021"},{"key":"2023071316415435300_bib23","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/ICCV.2019.00019","article-title":"NLNL: Negative learning for noisy labels","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV","author":"Kim","year":"2019"},{"key":"2023071316415435300_bib24","first-page":"3488","article-title":"Robust learning from untrusted sources","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Konstantinov","year":"2019"},{"key":"2023071316415435300_bib25","first-page":"896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Workshop on challenges in representation learning, ICML","author":"Lee","year":"2013"},{"key":"2023071316415435300_bib26","doi-asserted-by":"publisher","first-page":"5447","DOI":"10.1109\/CVPR.2018.00571","article-title":"CleanNet: Transfer learning for scalable image classifier training with label noise","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR","author":"Lee","year":"2018"},{"key":"2023071316415435300_bib27","doi-asserted-by":"publisher","first-page":"7871","DOI":"10.18653\/v1\/2020.acl-main.703","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL","author":"Lewis","year":"2020"},{"key":"2023071316415435300_bib28","doi-asserted-by":"publisher","first-page":"5044","DOI":"10.18653\/v1\/2021.acl-long.391","article-title":"Semi-supervised text classification with balanced deep representation distributions","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP","author":"Li","year":"2021"},{"key":"2023071316415435300_bib29","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proceedings of the 8th International Conference on Learning Representations, ICLR","author":"Li","year":"2020"},{"key":"2023071316415435300_bib30","first-page":"218","article-title":"Negative training data can be harmful to text classification","volume-title":"Proceedings of Empirical Methods in Natural Language Processing, EMNLP","author":"Li","year":"2010"},{"key":"2023071316415435300_bib31","doi-asserted-by":"publisher","DOI":"10.3115\/1072228.1072378","article-title":"Learning question classifiers","volume-title":"Proceedings of the 19th International Conference on Computational Linguistics, COLING","author":"Li","year":"2002"},{"issue":"1","key":"2023071316415435300_bib32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-02145-9","article-title":"Sentiment analysis and opinion mining","volume":"5","author":"Liu","year":"2012","journal-title":"Synthesis Lectures on Human Language Technologies"},{"key":"2023071316415435300_bib33","first-page":"387","article-title":"Partially supervised classification of text documents","volume-title":"Proceedings of the Nineteenth International Conference ICML","author":"Liu","year":"2002"},{"key":"2023071316415435300_bib34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7969","article-title":"Partially supervised text classification with multi-level examples","volume-title":"Proceedings of the Twenty-Fifth Conference on Artificial Intelligence, AAAI","author":"Liu","year":"2011"},{"key":"2023071316415435300_bib35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.11692","article-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","author":"Liu","year":"2019","journal-title":"CoRR"},{"issue":"5","key":"2023071316415435300_bib36","doi-asserted-by":"publisher","first-page":"1605","DOI":"10.1109\/TCYB.2017.2710205","article-title":"Classifier fusion with contextual reliability evaluation","volume":"48","author":"Liu","year":"2018","journal-title":"IEEE Transactions on Cybernetics"},{"key":"2023071316415435300_bib37","doi-asserted-by":"publisher","first-page":"4068","DOI":"10.24963\/ijcai.2017\/568","article-title":"Interactive attention networks for aspect-level sentiment classification","volume-title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI","author":"Ma","year":"2017"},{"key":"2023071316415435300_bib38","doi-asserted-by":"publisher","first-page":"6201","DOI":"10.18653\/v1\/2021.acl-long.484","article-title":"SENT: Sentence-level distant relation extraction via negative training","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP","author":"Ma","year":"2021"},{"key":"2023071316415435300_bib39","first-page":"3355","article-title":"Dimensionality-driven learning with noisy labels","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Ma","year":"2018"},{"key":"2023071316415435300_bib40","doi-asserted-by":"publisher","first-page":"arXiv:1605.07725","DOI":"10.48550\/arXiv.1605.07725","article-title":"Adversarial training methods for semi-supervised text classification","author":"Miyato","year":"2016","journal-title":"arXiv e-prints"},{"issue":"8","key":"2023071316415435300_bib41","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","article-title":"Virtual adversarial training: A regularization method for supervised and semi-supervised learning","volume":"41","author":"Miyato","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2023071316415435300_bib42","article-title":"Uncertainty-aware Self-training for Few-shot Text Classification","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems NeurIPS","author":"Mukherjee","year":"2020"},{"issue":"18","key":"2023071316415435300_bib43","doi-asserted-by":"publisher","first-page":"14719","DOI":"10.1007\/s00521-020-04824-8","article-title":"Constructing domain-dependent sentiment dictionary for sentiment analysis","volume":"32","author":"Murtadha","year":"2020","journal-title":"Neural Computing & Applications"},{"key":"2023071316415435300_bib44","doi-asserted-by":"publisher","first-page":"115","DOI":"10.3115\/1219840.1219855","article-title":"Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales","volume-title":"Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics ACL","author":"Bo","year":"2005"},{"key":"2023071316415435300_bib45","doi-asserted-by":"publisher","first-page":"2233","DOI":"10.1109\/CVPR.2017.240","article-title":"Making deep neural networks robust to label noise: A loss correction approach","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Patrini","year":"2017"},{"issue":"3","key":"2023071316415435300_bib46","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1109\/TKDE.2015.2485209","article-title":"Survey on aspect-level sentiment analysis","volume":"28","author":"Schouten","year":"2016","journal-title":"IEEE Transactions on Knowledge and Data Engineering TKDE"},{"key":"2023071316415435300_bib47","first-page":"5739","article-title":"Learning with bad training data via iterative trimmed loss minimization","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Shen","year":"2019"},{"key":"2023071316415435300_bib48","first-page":"455","article-title":"Parsing with compositional vector grammars","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL","author":"Socher","year":"2013"},{"key":"2023071316415435300_bib49","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proceedings of Empirical Methods in Natural Language Processing, EMNLP","author":"Socher","year":"2013"},{"key":"2023071316415435300_bib50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30490-4_9","article-title":"Attentional encoder network for targeted sentiment classification","author":"Song","year":"2019","journal-title":"CoRR"},{"key":"2023071316415435300_bib51","doi-asserted-by":"publisher","first-page":"286","DOI":"10.18653\/v1\/D19-5537","article-title":"Contextual text denoising with masked language model","volume-title":"Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT)","author":"Sun","year":"2019"},{"key":"2023071316415435300_bib52","first-page":"6234","article-title":"Combating label noise in deep learning using abstention","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Thulasidasan","year":"2019"},{"key":"2023071316415435300_bib53","doi-asserted-by":"publisher","first-page":"11394","DOI":"10.1609\/aaai.v36i10.21391","article-title":"Contrast-enhanced semi-supervised text classification with few labels","volume-title":"Proceedings of the Thirty-Sixth Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI","author":"Tsai","year":"2022"},{"key":"2023071316415435300_bib54","article-title":"Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks","volume-title":"Proceedings of the Neural Information Processing Systems NeurPIS","author":"Vahdat","year":"2017"},{"key":"2023071316415435300_bib55","doi-asserted-by":"publisher","first-page":"6575","DOI":"10.1109\/CVPR.2017.696","article-title":"Learning from noisy large-scale datasets with minimal supervision","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR","author":"Veit","year":"2017"},{"key":"2023071316415435300_bib56","doi-asserted-by":"publisher","first-page":"5265","DOI":"10.1109\/CVPR.2018.00552","article-title":"CosFace: Large margin cosine loss for deep face recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR","author":"Wang","year":"2018"},{"key":"2023071316415435300_bib57","doi-asserted-by":"publisher","first-page":"106509","DOI":"10.1016\/j.knosys.2020.106509","article-title":"Aspect-level sentiment analysis based on gradual machine learning","volume":"212","author":"Wang","year":"2021","journal-title":"Knowledge-based Systems, KBS"},{"key":"2023071316415435300_bib58","doi-asserted-by":"publisher","first-page":"606","DOI":"10.18653\/v1\/D16-1058","article-title":"Attention-based LSTM for aspect-level sentiment classification","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP","author":"Wang","year":"2016"},{"key":"2023071316415435300_bib59","doi-asserted-by":"publisher","first-page":"2691","DOI":"10.1109\/CVPR.2015.7298885","article-title":"Learning from massive noisy labeled data for image classification","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR","author":"Xiao","year":"2015"},{"key":"2023071316415435300_bib60","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proceedings of the Annual Conferenceon Neural Information Processing Systems","author":"Xie","year":"2020"},{"key":"2023071316415435300_bib61","doi-asserted-by":"publisher","first-page":"4762","DOI":"10.18653\/v1\/2020.coling-main.419","article-title":"CLUE: A Chinese language understanding evaluation benchmark","volume-title":"Proceedings of the 28th International Conference on Computational Linguistics, COLING","author":"Liang","year":"2020"},{"key":"2023071316415435300_bib62","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2013.09.003","article-title":"Evidential reasoning rule for evidence combination","volume":"205","author":"Yang","year":"2013","journal-title":"Artificial Intelligence"},{"key":"2023071316415435300_bib63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2022.3220219","article-title":"A survey on deep semi-supervised learning","author":"Yang","year":"2022","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2023071316415435300_bib64","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems NeurIPS","author":"Yang","year":"2019"},{"key":"2023071316415435300_bib65","first-page":"3881","article-title":"Improved variational autoencoders for text modeling using dilated convolutions","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML","author":"Yang","year":"2017"},{"key":"2023071316415435300_bib66","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Xingrui","year":"2019"},{"key":"2023071316415435300_bib67","article-title":"Big Bird: Transformers for longer sequences","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems, NeurIPS","author":"Zaheer","year":"2020"},{"issue":"3","key":"2023071316415435300_bib68","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","article-title":"Understanding deep learning (still) requires rethinking generalization","volume":"64","author":"Zhang","year":"2021","journal-title":"Communications of the ACM"},{"key":"2023071316415435300_bib69","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume-title":"Annual Conference on Neural Information Processing Systems","author":"Zhang","year":"2015"}],"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_00574\/2143272\/tacl_a_00574.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00574\/2143272\/tacl_a_00574.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T16:42:29Z","timestamp":1689266549000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00574\/116712\/Rank-Aware-Negative-Training-for-Semi-Supervised"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00574","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}