{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:11:46Z","timestamp":1776057106523,"version":"3.50.1"},"reference-count":30,"publisher":"China Science Publishing & Media Ltd.","issue":"3","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"vor","delay-in-days":8,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n               <jats:p>Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks. Recently, few-shot models have been used for Named Entity Recognition (NER). Prototypical network shows high efficiency on few-shot NER. However, existing prototypical methods only consider the similarity of tokens in query sets and support sets and ignore the semantic similarity among the sentences which contain these entities. We present a novel model, Few-shot Named Entity Recognition with Joint Token and Sentence Awareness (JTSA), to address the issue. The sentence awareness is introduced to probe the semantic similarity among the sentences. The Token awareness is used to explore the similarity of the tokens. To further improve the robustness and results of the model, we adopt the joint learning scheme on the few-shot NER. Experimental results demonstrate that our model outperforms state-of-the-art models on two standard Few-shot NER datasets.<\/jats:p>","DOI":"10.1162\/dint_a_00195","type":"journal-article","created":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T20:54:36Z","timestamp":1673297676000},"page":"767-785","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":9,"title":["Few-shot Named Entity Recognition with Joint Token and Sentence Awareness"],"prefix":"10.3724","volume":"5","author":[{"given":"Wen","family":"Wen","sequence":"first","affiliation":[{"name":"Computer School, University of South China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongbin","family":"Liu","sequence":"additional","affiliation":[{"name":"Computer School, University of South China, China"},{"name":"Hunan provincial base for scientific and technological innovation cooperation, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Computer School, University of South China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunping","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Computer School, University of South China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"2026","published-online":{"date-parts":[[2023,8,1]]},"reference":[{"key":"2023091215380293400_ref1","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"ICML Deep Learning Workshop","author":"Koch","year":"2015"},{"key":"2023091215380293400_ref2","first-page":"3630","article-title":"Matching networks for one shot learning","volume-title":"Advances in Neural Information Processing Systems","author":"Vinyals","year":"2016"},{"key":"2023091215380293400_ref3","first-page":"1199","article-title":"Learning to compare: Relation network for few-shot learning","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Sung","year":"2018"},{"key":"2023091215380293400_ref4","first-page":"4077","article-title":"Prototypical networks for few-shot learning","volume-title":"Advances in Neural Information Processing Systems","author":"Snell","year":"2017"},{"key":"2023091215380293400_ref5","doi-asserted-by":"crossref","first-page":"4803","DOI":"10.18653\/v1\/D18-1514","article-title":"Fewrel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Han","year":"2018"},{"key":"2023091215380293400_ref6","doi-asserted-by":"crossref","first-page":"6407","DOI":"10.1609\/aaai.v33i01.33016407","article-title":"Hybrid attention-based prototypical networks for noisy few-shot relation classification","volume":"33","author":"Gao","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2023091215380293400_ref7","volume-title":"Prototypical representation learning for relation extraction","author":"Ding","year":"2021"},{"key":"2023091215380293400_ref8","volume-title":"Free lunch for few-shot learning: Distribution calibration","author":"Yang","year":"2021"},{"key":"2023091215380293400_ref9","doi-asserted-by":"crossref","DOI":"10.1145\/3297280.3297378","article-title":"Few-shot classification in named entity recognition task","volume-title":"Proceedings of the 34th ACM\/SIGAPP Symposium on Applied Computing","author":"Kretov Fritzler","year":"2019"},{"key":"2023091215380293400_ref10","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.acl-long.487","article-title":"Learning from miscellaneous other-class words for few-shot named entity recognition","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":"Tong","year":"2021"},{"key":"2023091215380293400_ref11","volume-title":"Fewjoint: A few-shot learning benchmark for joint language understanding","author":"Hou","year":"2020"},{"key":"2023091215380293400_ref12","volume-title":"Few-nerd: A few-shot named entity recognition dataset","author":"Ding","year":"2021"},{"key":"2023091215380293400_ref13","article-title":"Message understanding conference 6: A brief history","volume-title":"Proceedings of the 16th conference on Computational linguistics - Volume 1","author":"Sundheim","year":"1996"},{"key":"2023091215380293400_ref14","article-title":"Introduction to the conll-2003 shared task: Language-independent named entity recognition","volume-title":"arXiv","author":"Sang","year":"2003"},{"key":"2023091215380293400_ref15","volume-title":"A survey on recent advances in named entity recognition from deep learning models","author":"Yadav","year":"2019"},{"key":"2023091215380293400_ref16","doi-asserted-by":"crossref","DOI":"10.1145\/1390156.1390177","article-title":"A unified architecture for natural language processing: deep neural networks with multitask learning","volume-title":"Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland","author":"Collobert","year":"2008"},{"key":"2023091215380293400_ref17","article-title":"Efficient estimation of word representations in vector space","volume-title":"Computer Science","author":"Mikolov","year":"2013"},{"key":"2023091215380293400_ref18","article-title":"Bidirectional lstm-crf models for sequence tagging","volume-title":"Computer Science","author":"Huang","year":"2015"},{"key":"2023091215380293400_ref19","volume-title":"Character-aware neural language models","author":"Kim","year":"2015"},{"key":"2023091215380293400_ref20","article-title":"Named entity recognition with bidirectional lstm-cnns","volume-title":"Computer Science","author":"Chiu","year":"2015"},{"key":"2023091215380293400_ref21","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N16-1030","article-title":"Neural architectures for named entity recognition","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Lample","year":"2016"},{"key":"2023091215380293400_ref22","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1510","article-title":"Nne: A dataset for nested named entity recognition in english newswire","volume-title":"Meeting of the Association for Computational Linguistics","author":"Ringland","year":"2019"},{"key":"2023091215380293400_ref23","doi-asserted-by":"publisher","first-page":"4071","DOI":"10.24963\/ijcai.2018\/566","article-title":"Improving low resource named entity recognition using cross-lingual knowledge transfer","volume-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18","author":"Feng","year":"2018"},{"key":"2023091215380293400_ref24","volume-title":"Few-shot learning for named entity recognition in medical text","author":"Hofer","year":"2018"},{"key":"2023091215380293400_ref25","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.emnlp-main.516","volume-title":"Simple and effective few-shot named entity recognition with structured nearest neighbor learning","author":"Yang","year":"2020"},{"key":"2023091215380293400_ref26","article-title":"Few-shot named entity recognition via meta-learning","volume-title":"IEEE Transactions on Knowledge and Data Engineering","author":"Li","year":"2020"},{"key":"2023091215380293400_ref27","volume-title":"Few-shot named entity recognition: A comprehensive study","author":"Huang","year":"2020"},{"key":"2023091215380293400_ref28","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"2023091215380293400_ref29","volume-title":"An enhanced span-based decomposition method for few-shot sequence labeling","author":"Wang","year":"2021"},{"key":"2023091215380293400_ref30","volume-title":"Container: Few-shot named entity recognition via contrastive learning","author":"Das","year":"2021"}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/3\/767\/2158274\/dint_a_00195.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/3\/767\/2158274\/dint_a_00195.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T23:07:13Z","timestamp":1741129633000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/dint\/article\/5\/3\/767\/114486\/Few-shot-Named-Entity-Recognition-with-Joint-Token"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":30,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,8,1]]}},"URL":"https:\/\/doi.org\/10.1162\/dint_a_00195","relation":{},"ISSN":["2641-435X"],"issn-type":[{"value":"2641-435X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}