{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T02:26:42Z","timestamp":1772677602416,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72071145"],"award-info":[{"award-number":["72071145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3637299","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:05:14Z","timestamp":1764183914000},"page":"207617-207637","source":"Crossref","is-referenced-by-count":1,"title":["Word Structure Embedding and In-Context Learning for Chinese Segmentation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0627-948X","authenticated-orcid":false,"given":"Zhongguo","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9714-1210","authenticated-orcid":false,"given":"Yang","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9","article-title":"Multi-paragraph segmentation of expository text","volume-title":"Proc. 32nd Annu. meeting Assoc. Comput. Linguistics","author":"Hearst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.844"},{"key":"ref3","first-page":"19308","article-title":"Segment-based attention masking for GPTs","volume-title":"Proc. 63rd Annu. Meeting Assoc. Comput. Linguistics","author":"Katz"},{"key":"ref4","first-page":"8063","article-title":"Document segmentation matters for retrieval-augmented generation","volume-title":"Proc. Findings Assoc. Comput. Linguistics (ACL)","author":"Wang"},{"key":"ref5","first-page":"26","article-title":"Advances in domain independent linear text segmentation","volume-title":"Proc. 6th Appl. Natural Lang. Process. Conf.","author":"Choi"},{"key":"ref6","first-page":"353","article-title":"Hierarchical text segmentation from multi-scale lexical cohesion","volume-title":"Proc. Human Lang. Technol., Annu. Conf. North Amer. Chapter Assoc. Comput. Linguistics (NAACL)","author":"Eisenstein"},{"key":"ref7","first-page":"125","article-title":"Unsupervised text segmentation using semantic relatedness graphs","volume-title":"Proc. 5th Joint Conf. Lexical Comput. Semantics","author":"Glava\u0161"},{"key":"ref8","first-page":"469","article-title":"Text segmentation as a supervised learning task","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Koshorek"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/579"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-76941-7_14"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.380"},{"key":"ref12","first-page":"7797","article-title":"Two-level transformer and auxiliary coherence modeling for improved text segmentation","volume-title":"Proc. AAAI","volume":"34","author":"Glavas"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688078"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1561\/9781601982957","volume-title":"Learning Deep Architectures for AI","author":"Bengio","year":"2009"},{"key":"ref15","article-title":"Dense X retrieval: What retrieval granularity should we use?","author":"Chen","year":"2023","journal-title":"arXiv:2312.06648"},{"key":"ref16","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.60"},{"key":"ref18","first-page":"3827","article-title":"GrIPS: Gradient-free, edit-based instruction search for prompting large language models","volume-title":"Proc. 17th Conf. Eur. Chapter Assoc. Comput. Linguistics","author":"Prasad"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"ref21","article-title":"Learning to retrieve in-context examples for large language models","author":"Wang","year":"2023","journal-title":"arXiv:2307.07164"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.79"},{"key":"ref24","article-title":"Generalization through memorization: Nearest neighbor languagemodels","author":"Khandelwal","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.214"},{"key":"ref26","first-page":"1","article-title":"KRNN prompting: Beyond-context learning with calibration-free nearest neighbor inference","volume-title":"Proc. The 11th Int. Conf. Learn. Represent. (ICLR)","author":"Xu"},{"key":"ref27","first-page":"1481","article-title":"Feature-adaptive and datascalable in-context learning","volume-title":"Proc. 62nd Annu. Meeting Assoc. Comput. Linguistics","author":"Li"},{"key":"ref28","article-title":"Parsing through boundaries in Chinese word segmentation","author":"Chen","year":"2025","journal-title":"arXiv:2503.23091"},{"key":"ref29","first-page":"24228","article-title":"GRaMPa: Subword regularisation by skewing uniform segmentation distributions with an efficient path-counting Markov model","volume-title":"Proc. 63rd Annu. Meeting Assoc. Comput. Linguistics","author":"Bauwens"},{"key":"ref30","first-page":"2379","article-title":"An encoding strategy based word-character","volume-title":"Proc. Conf. North","author":"Liu"},{"key":"ref31","first-page":"1462","article-title":"A neural multi-digraph model for Chinese NER with gazetteers","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Ding"},{"key":"ref32","first-page":"3384","article-title":"CAN-NER: Convolutional attention network for Chinese named entity recognition","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Zhu"},{"key":"ref33","first-page":"5951","article-title":"Simplify the usage of lexicon in Chinese NER","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Ma"},{"key":"ref34","first-page":"1591","article-title":"Characterlevel translation with self-attention","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Gao"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1144"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/692"},{"key":"ref37","first-page":"464","article-title":"Self-attention with relative position representations","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Computational Linguistics, Human Lang. Technol.","volume":"2","author":"Shaw"},{"key":"ref38","first-page":"2978","article-title":"Transformer-XL: Attentive language models beyond a fixed-length context","volume-title":"Proc. 57th Annual Meeting Assoc. Comput. Linguistics","author":"Dai"},{"key":"ref39","article-title":"TENER: Adapting transformer encoder for named entity recognition","author":"Yan","year":"2019","journal-title":"arXiv:1911.04474"},{"key":"ref40","first-page":"3090","article-title":"Lattice-based transformer encoder for neural machine translation","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Xiao"},{"key":"ref41","first-page":"6836","article-title":"FLAT: Chinese NER using flat-lattice transformer","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Li"},{"key":"ref42","article-title":"NFLAT: Non-flat-lattice transformer for Chinese named entity recognition","author":"Wu","year":"2022","journal-title":"arXiv:2205.05832"},{"key":"ref43","first-page":"1040","article-title":"A lexicon-based graph neural network for Chinese NER","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Gui"},{"key":"ref44","first-page":"3830","article-title":"Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Sui"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.201"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.53"},{"key":"ref47","first-page":"500","article-title":"UniICL: An efficient ICL framework unifying compression, selection, and generation","volume-title":"Proc. 63rd Annu. Meeting Assoc. Comput. Linguistics","author":"Gao"},{"key":"ref48","article-title":"Efficient universal models for medical image segmentation via weakly supervised in-context learning","author":"Hu","year":"2025","journal-title":"arXiv:2510.05899"},{"key":"ref49","article-title":"Memory-augmented transformers: A systematic review from neuroscience principles to enhanced model architectures","author":"Omidi","year":"2025","journal-title":"arXiv:2508.10824"},{"key":"ref50","article-title":"Structured prompting: Scaling in-context learning to 1,000 examples","author":"Hao","year":"2022","journal-title":"arXiv:2212.06713"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1475"},{"key":"ref52","first-page":"3502","article-title":"Hierarchical document refinement for long-context retrieval-augmented generation","volume-title":"Proc. 63rd Annu. Meeting Assoc. Comput. Linguistics","author":"Jin"},{"key":"ref53","article-title":"Advancing topic segmentation and outline generation in Chinese texts: The paragraph-level topic representation, corpus, and benchmark","author":"Jiang","year":"2023","journal-title":"arXiv:2305.14790"},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.3758\/s13428-024-02528-8","article-title":"Acorpus of chineseword segmentation agreement","volume":"57","author":"Tsang","year":"2024","journal-title":"Behav. Res. Methods"},{"key":"ref55","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"ref56","article-title":"Representation learning on graphs: Methods and applications","author":"Hamilton","year":"2017","journal-title":"arXiv:1709.05584"},{"key":"ref57","author":"Henry","year":"2003","journal-title":"The Complete Stories by O. Henry"},{"key":"ref58","author":"Sun","year":"2016","journal-title":"Thuctc: An Efficient Chinese Text Classifier"},{"key":"ref59","doi-asserted-by":"crossref","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 Trans. Audio, Speech, Lang., Process."},{"key":"ref60","first-page":"839","article-title":"Neural word segmentation with rich pretraining","volume-title":"Proc. 55th Annu. Meeting Assoc. Comput. Linguistics","author":"Yang"},{"key":"ref61","first-page":"108","article-title":"API design for machine learning software: Experiences from the scikit-learn project","volume-title":"Proc. ECML PKDD Workshop: Lang. Data Mining Mach. Learn.","author":"Buitinck"},{"key":"ref62","first-page":"146","article-title":"Pause and stop labeling for Chinese sentence boundary detection","volume-title":"Proc. Int. Conf. Recent Adv. Natural Lang. Process.","author":"Huang"},{"key":"ref63","first-page":"3502","article-title":"RoChBert: Towards robust BERT fine-tuning for Chinese","volume-title":"Proc. Findings Assoc. Comput. Linguistics (EMNLP)","author":"Zhang"},{"key":"ref64","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref65","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017","journal-title":"arXiv:1703.05175"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34712"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11269686.pdf?arnumber=11269686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:19:37Z","timestamp":1766132377000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11269686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3637299","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}