{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T20:04:25Z","timestamp":1779134665432,"version":"3.51.4"},"reference-count":78,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"vor","delay-in-days":357,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarce text classification. However, existing CSAL methods overlook weak classes and hard representative examples, resulting in biased learning. To address these issues, this paper proposes a novel dual-diversity enhancing and uncertainty-aware (Deuce) framework for CSAL. Specifically, Deuce leverages a pretrained language model (PLM) to efficiently extract textual representations, class predictions, and predictive uncertainty. Then, it constructs a Dual-Neighbor Graph (DNG) to combine information on both textual diversity and class diversity, ensuring a balanced data distribution. It further propagates uncertainty information via density-based clustering to select hard representative instances. Deuce performs well in selecting class-balanced and hard representative data by dual-diversity and informativeness. Experiments on six NLP datasets demonstrate the superiority and efficiency of Deuce.<\/jats:p>","DOI":"10.1162\/tacl_a_00731","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T20:12:21Z","timestamp":1734984741000},"page":"1736-1754","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":3,"title":["<scp>Deuce<\/scp>: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning"],"prefix":"10.1162","volume":"12","author":[{"given":"Jiaxin","family":"Guo","sequence":"first","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"},{"name":"Pazhou Lab, Guangzhou, China"},{"name":"Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human, Guangzhou, China cs_guojiaxin@mail.scut.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. L.","family":"Philip Chen","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"},{"name":"Pazhou Lab, Guangzhou, China"},{"name":"Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human, Guangzhou, China philipchen@scut.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuzhen","family":"Li","sequence":"additional","affiliation":[{"name":"Pazhou Lab, Guangzhou, China"},{"name":"Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human, Guangzhou, China cslishuzhen@mail.scut.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"},{"name":"Pazhou Lab, Guangzhou, China"},{"name":"Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human, Guangzhou, China tony@scut.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"2025011417400979000_bib1","article-title":"Addressing practical challenges in active learning via a hybrid query strategy","author":"Agarwal","year":"2021","journal-title":"arXiv preprint arXiv:2110.03785v1"},{"key":"2025011417400979000_bib2","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1109\/WACV45572.2020.9093475","article-title":"Active learning for imbalanced datasets","volume-title":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"Aggarwal","year":"2020"},{"key":"2025011417400979000_bib3","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1145\/3644815.3644967","article-title":"Green AI: A preliminary empirical study on energy consumption in DL models across different runtime infrastructures","volume-title":"Proceedings of the IEEE\/ACM 3rd International Conference on AI Engineering - Software Engineering for AI","author":"Alizadeh","year":"2024"},{"key":"2025011417400979000_bib4","article-title":"Deep batch active learning by diverse, uncertain gradient lower bounds","volume-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","author":"Ash","year":"2020"},{"key":"2025011417400979000_bib5","article-title":"Cold start active learning strategies in the context of imbalanced classification","author":"Brangbour","year":"2022","journal-title":"arXiv preprint arXiv:2201.10227v1"},{"key":"2025011417400979000_bib6","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-642-37456-2_14","article-title":"Density-based clustering based on hierarchical density estimates","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Campello","year":"2013"},{"issue":"1","key":"2025011417400979000_bib7","doi-asserted-by":"publisher","DOI":"10.1145\/2733381","article-title":"Hierarchical density estimates for data clustering, visualization, and outlier detection","volume":"10","author":"Campello","year":"2015","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"2025011417400979000_bib8","doi-asserted-by":"publisher","first-page":"8","DOI":"10.18653\/v1\/2021.acl-short.2","article-title":"On training instance selection for few-shot neural text generation","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)","author":"Chang","year":"2021"},{"key":"2025011417400979000_bib9","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint arXiv:2110.14168v2"},{"key":"2025011417400979000_bib10","doi-asserted-by":"publisher","first-page":"701","DOI":"10.3115\/1690219.1690244","article-title":"Mine the easy, classify the hard: A semi-supervised approach to automatic sentiment classification","volume-title":"Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP","author":"Dasgupta","year":"2009"},{"issue":"19","key":"2025011417400979000_bib11","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1016\/j.tcs.2010.12.054","article-title":"Two faces of active learning","volume":"412","author":"Dasgupta","year":"2011","journal-title":"Theoretical Computer Science"},{"issue":"1","key":"2025011417400979000_bib12","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-021-04047-1","article-title":"Deep active learning for classifying cancer pathology reports","volume":"22","author":"De Angeli","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2025011417400979000_bib13","first-page":"6","article-title":"Good seed makes a good crop: Accelerating active learning using language modeling","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"Dligach","year":"2011"},{"issue":"1","key":"2025011417400979000_bib14","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1080\/03081078208934833","article-title":"A class of fuzzy measures based on triangular norms: A general framework for the combination of uncertain information","volume":"8","author":"Dubois","year":"1982","journal-title":"International Journal of General Systems"},{"key":"2025011417400979000_bib15","doi-asserted-by":"publisher","first-page":"7949","DOI":"10.18653\/v1\/2020.emnlp-main.638","article-title":"Active learning for BERT: An empirical study","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Ein-Dor","year":"2020"},{"key":"2025011417400979000_bib16","doi-asserted-by":"publisher","first-page":"635","DOI":"10.18653\/v1\/2022.emnlp-industry.65","article-title":"Topic modeling by clustering language model embeddings: Human validation on an industry dataset","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track","author":"Eklund","year":"2022"},{"key":"2025011417400979000_bib17","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1109\/ICPR.1994.577129","article-title":"The farthest point strategy for progressive image sampling","volume-title":"Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 2 - Conference B: Computer Vision & Image Processing. (Cat. No.94CH3440-5)","author":"Eldar","year":"1994"},{"key":"2025011417400979000_bib18","first-page":"77","article-title":"Class balancing for efficient active learning in imbalanced datasets","volume-title":"Proceedings of The 18th Linguistic Annotation Workshop (LAW-XVIII)","author":"Fairstein","year":"2024"},{"key":"2025011417400979000_bib19","article-title":"Representation degeneration problem in training natural language generation models","volume-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019","author":"Gao","year":"2019"},{"key":"2025011417400979000_bib20","doi-asserted-by":"publisher","first-page":"6894","DOI":"10.18653\/v1\/2021.emnlp-main.552","article-title":"SimCSE: Simple contrastive learning of sentence embeddings","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Gao","year":"2021"},{"key":"2025011417400979000_bib21","doi-asserted-by":"publisher","first-page":"1130","DOI":"10.1109\/BIBM47256.2019.8983025","article-title":"Sentiment analysis using autoregressive language modeling and broad learning system","volume-title":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Gong","year":"2019"},{"key":"2025011417400979000_bib22","first-page":"8175","article-title":"Active learning on a budget: Opposite strategies suit high and low budgets","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Hacohen","year":"2022"},{"key":"2025011417400979000_bib23","first-page":"5549","article-title":"TabLLM: Few-shot classification of tabular data with large language models","volume-title":"Proceedings of The 26th International Conference on Artificial Intelligence and Statistics","author":"Hegselmann","year":"2023"},{"key":"2025011417400979000_bib24","doi-asserted-by":"publisher","first-page":"166970","DOI":"10.1109\/ACCESS.2021.3135514","article-title":"A survey on cost types, interaction schemes, and annotator performance models in selection algorithms for active learning in classification","volume":"9","author":"Herde","year":"2021","journal-title":"IEEE Access"},{"issue":"2","key":"2025011417400979000_bib25","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s40708-016-0042-6","article-title":"Interactive machine learning for health informatics: When do we need the human-in-the-loop?","volume":"3","author":"Holzinger","year":"2016","journal-title":"Brain Informatics"},{"key":"2025011417400979000_bib26","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25\u201329, 2022","author":"Edward","year":"2022"},{"key":"2025011417400979000_bib27","article-title":"Off to a good start: Using clustering to select the initial training set in active learning","volume-title":"Proceedings of the Twenty-Third International Florida Artificial Intelligence Research Society Conference, May 19\u201321, 2010, Daytona Beach, Florida, USA","author":"Rong","year":"2010"},{"key":"2025011417400979000_bib28","article-title":"Scaling sentence embeddings with large language models","author":"Jiang","year":"2023","journal-title":"arXiv preprint arXiv:2307.16645v1"},{"key":"2025011417400979000_bib29","doi-asserted-by":"publisher","first-page":"8826","DOI":"10.18653\/v1\/2022.emnlp-main.603","article-title":"PromptBERT: Improving BERT sentence embeddings with prompts","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Jiang","year":"2022"},{"key":"2025011417400979000_bib30","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1162\/tacl_a_00407","article-title":"How can we know when language models know? On the calibration of language models for question answering","volume":"9","author":"Jiang","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2025011417400979000_bib31","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1007\/978-3-540-24775-3_46","article-title":"Using cluster-based sampling to select initial training set for active learning in text classification","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Kang","year":"2004"},{"key":"2025011417400979000_bib32","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Advances in Neural Information Processing Systems","author":"Kojima","year":"2022"},{"key":"2025011417400979000_bib33","article-title":"Mitigating sampling bias and improving robustness in active learning","volume-title":"Proceedings of Workshop on Human in the Loop Learning (HILL) in International Conference on Machine Learning (ICML 2021)","author":"Krishnan","year":"2021"},{"issue":"2","key":"2025011417400979000_bib34","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3233\/SW-140134","article-title":"DBpedia \u2013 a large-scale, multilingual knowledge base extracted from Wikipedia","volume":"6","author":"Lehmann","year":"2015","journal-title":"Semantic Web"},{"key":"2025011417400979000_bib35","doi-asserted-by":"publisher","DOI":"10.3115\/1072228.1072378","article-title":"Learning question classifiers","volume-title":"COLING 2002: The 19th International Conference on Computational Linguistics","author":"Li","year":"2002"},{"key":"2025011417400979000_bib36","article-title":"Privacy-preserving prompt tuning for large language model services","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv:2305.06212v1"},{"key":"2025011417400979000_bib37","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692v1"},{"key":"2025011417400979000_bib38","article-title":"Human still wins over LLM: An empirical study of active learning on domain-specific annotation tasks","author":"Yuxuan","year":"2023","journal-title":"arXiv preprint arXiv:2311.09825v1"},{"key":"2025011417400979000_bib39","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"Maas","year":"2011"},{"issue":"86","key":"2025011417400979000_bib40","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"2025011417400979000_bib41","doi-asserted-by":"publisher","first-page":"898","DOI":"10.3115\/v1\/D14-1097","article-title":"An experimental comparison of active learning strategies for partially labeled sequences","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Marcheggiani","year":"2014"},{"key":"2025011417400979000_bib42","doi-asserted-by":"publisher","first-page":"650","DOI":"10.18653\/v1\/2021.emnlp-main.51","article-title":"Active learning by acquiring contrastive examples","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Margatina","year":"2021"},{"key":"2025011417400979000_bib43","article-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2020","journal-title":"arXiv preprint arXiv:1802.03426v3"},{"issue":"29","key":"2025011417400979000_bib44","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: Uniform manifold approximation and projection","volume":"3","author":"McInnes","year":"2018","journal-title":"Journal of Open Source Software"},{"issue":"01","key":"2025011417400979000_bib45","doi-asserted-by":"publisher","first-page":"6826","DOI":"10.1609\/aaai.v33i01.33016826","article-title":"Weakly-supervised hierarchical text classification","volume":"33","author":"Meng","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2025011417400979000_bib46","doi-asserted-by":"publisher","first-page":"1847","DOI":"10.1145\/3583780.3614833","article-title":"DebCSE: Rethinking unsupervised contrastive sentence embedding learning in the debiasing perspective","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","author":"Miao","year":"2023"},{"key":"2025011417400979000_bib47","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/978-3-031-08473-7_9","article-title":"Active few-shot learning with FASL","volume-title":"Natural Language Processing and Information Systems; 27th International Conference on Applications of Natural Language to Information Systems, NLDB 2022, Valencia, Spain, June 15\u201317, 2022, Proceedings","author":"M\u00fcller","year":"2022"},{"key":"2025011417400979000_bib48","article-title":"Large language models are fixated by red herrings: Exploring creative problem solving and Einstellung effect using the Only Connect Wall dataset","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Naeini","year":"2023"},{"key":"2025011417400979000_bib49","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1145\/1015330.1015349","article-title":"Active learning using pre-clustering","volume-title":"Proceedings of the Twenty-First International Conference on Machine Learning","author":"Nguyen","year":"2004"},{"key":"2025011417400979000_bib50","article-title":"Pervasive label errors in test sets destabilize machine learning benchmarks","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","author":"Northcutt","year":"2021"},{"key":"2025011417400979000_bib51","article-title":"Revisiting one-vs-all classifiers for predictive uncertainty and out-of-distribution detection in neural networks","volume-title":"ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning","author":"Padhy","year":"2020"},{"key":"2025011417400979000_bib52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2024.3352100","article-title":"Unifying large language models and knowledge graphs: A roadmap","author":"Pan","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2025011417400979000_bib53","doi-asserted-by":"publisher","first-page":"5364","DOI":"10.18653\/v1\/2022.acl-long.368","article-title":"On the calibration of pre-trained language models using mixup guided by area under the margin and saliency","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Park","year":"2022"},{"issue":"1","key":"2025011417400979000_bib54","doi-asserted-by":"publisher","first-page":"20230022","DOI":"10.1515\/jci-2023-0022","article-title":"All models are wrong, but which are useful? Comparing parametric and nonparametric estimation of causal effects in finite samples","volume":"11","author":"Rudolph","year":"2023","journal-title":"Journal of Causal Inference"},{"key":"2025011417400979000_bib55","doi-asserted-by":"publisher","first-page":"2194","DOI":"10.18653\/v1\/2022.findings-acl.172","article-title":"Revisiting uncertainty-based query strategies for active learning with transformers","volume-title":"Findings of the Association for Computational Linguistics: ACL 2022","author":"Schr\u00f6der","year":"2022"},{"key":"2025011417400979000_bib56","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1145\/1183614.1183709","article-title":"Performance thresholding in practical text classification","volume-title":"Proceedings of the 15th ACM International Conference on Information and Knowledge Management","author":"Sch\u00fctze","year":"2006"},{"key":"2025011417400979000_bib57","article-title":"Active learning for convolutional neural networks: A core-set approach","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 \u2013 May 3, 2018, Conference Track Proceedings","author":"Sener","year":"2018"},{"key":"2025011417400979000_bib58","article-title":"paraphrase-mpnet-base-v2 (revision e6981e5)","author":"Transformers","year":"2024"},{"key":"2025011417400979000_bib59","unstructured":"Burr\n              Settles\n            \n          . 2009. Active learning literature survey. Computer Sciences Technical Report 1648, University of Wisconsin\u2013Madison."},{"key":"2025011417400979000_bib60","doi-asserted-by":"publisher","first-page":"7639","DOI":"10.18653\/v1\/2022.acl-long.526","article-title":"Cluster & tune: Boost cold start performance in text classification","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Shnarch","year":"2022"},{"key":"2025011417400979000_bib61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095738","article-title":"Selective annotation makes language models better few-shot learners","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023","author":"Hongjin","year":"2023"},{"key":"2025011417400979000_bib62","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3115\/1564131.1564135","article-title":"On proper unit selection in active learning: Co-selection effects for named entity recognition","volume-title":"Proceedings of the NAACL HLT 2009 Workshop on Active Learning for Natural Language Processing","author":"Tomanek","year":"2009"},{"key":"2025011417400979000_bib63","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288v2"},{"key":"2025011417400979000_bib64","article-title":"Calibration in deep learning: A survey of the state-of-the-art","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2308.01222v2"},{"key":"2025011417400979000_bib65","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Advances in Neural Information Processing Systems","author":"Wei","year":"2022"},{"key":"2025011417400979000_bib66","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1016\/j.future.2022.05.014","article-title":"A survey of human-in-the-loop for machine learning","volume":"135","author":"Xingjiao","year":"2022","journal-title":"Future Generation Computer Systems"},{"key":"2025011417400979000_bib67","doi-asserted-by":"publisher","first-page":"109219","DOI":"10.1016\/j.asoc.2022.109219","article-title":"SLOVA: Uncertainty estimation using single label one-vs-all classifier","volume":"126","author":"W\u00f3jcik","year":"2022","journal-title":"Applied Soft Computing"},{"key":"2025011417400979000_bib68","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Advances in Neural Information Processing Systems","author":"Yang","year":"2019"},{"issue":"4","key":"2025011417400979000_bib69","doi-asserted-by":"publisher","first-page":"1088","DOI":"10.1109\/TNNLS.2018.2855446","article-title":"Active learning from imbalanced data: A solution of online weighted extreme learning machine","volume":"30","author":"Hualong","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2025011417400979000_bib70","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.18653\/v1\/2023.acl-long.141","article-title":"Cold-start data selection for better few-shot language model fine-tuning: A prompt-based uncertainty propagation approach","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Yue","year":"2023"},{"key":"2025011417400979000_bib71","doi-asserted-by":"publisher","first-page":"7935","DOI":"10.18653\/v1\/2020.emnlp-main.637","article-title":"Cold-start active learning through self-supervised language modeling","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Yuan","year":"2020"},{"key":"2025011417400979000_bib72","doi-asserted-by":"publisher","first-page":"1858","DOI":"10.1109\/ICDE48307.2020.00188","article-title":"Comprehensive and efficient data labeling via adaptive model scheduling","volume-title":"2020 IEEE 36th International Conference on Data Engineering (ICDE)","author":"Yuan","year":"2020"},{"key":"2025011417400979000_bib73","article-title":"Utilising a large language model to annotate subject metadata: A case study in an Australian national research data catalogue","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2310.11318v1"},{"issue":"7","key":"2025011417400979000_bib74","doi-asserted-by":"publisher","first-page":"6232","DOI":"10.1109\/TCYB.2021.3050508","article-title":"BMT-Net: Broad multitask transformer network for sentiment analysis","volume":"52","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"2","key":"2025011417400979000_bib75","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1109\/TSMC.2018.2884996","article-title":"Hierarchical lifelong learning by sharing representations and integrating hypothesis","volume":"51","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"2025011417400979000_bib76","article-title":"Character-level convolutional networks for text classification","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang","year":"2015"},{"key":"2025011417400979000_bib77","doi-asserted-by":"publisher","first-page":"6166","DOI":"10.18653\/v1\/2022.emnlp-main.414","article-title":"A survey of active learning for natural language processing","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Zhang","year":"2022"},{"key":"2025011417400979000_bib78","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.3115\/1599081.1599224","article-title":"Active learning with sampling by uncertainty and density for word sense disambiguation and text classification","volume-title":"Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)","author":"Zhu","year":"2008"}],"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_00731\/2487035\/tacl_a_00731.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00731\/2487035\/tacl_a_00731.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T17:40:31Z","timestamp":1736876431000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00731\/125950\/Deuce-Dual-diversity-Enhancement-and-Uncertainty"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00731","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}