{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:31:01Z","timestamp":1760401861289,"version":"build-2065373602"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-04411-5","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T11:33:47Z","timestamp":1760355227000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Segment-Based Bag of Clusters with Mixture Models and Late Chunking for Document Clustering"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2715-7647","authenticated-orcid":false,"given":"Quoc-Khang","family":"Tran","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6761-1636","authenticated-orcid":false,"given":"Nguyen-Khang","family":"Pham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"4411_CR1","unstructured":"Arthur D, Vassilvitskii S. k-means++: the advantages of careful seeding. In Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA \u201907. Society for Industrial and Applied Mathematics. 2007. p. 1027\u20131035"},{"key":"4411_CR2","doi-asserted-by":"crossref","unstructured":"Bafna P, Pramod D, Vaidya A. Document clustering: Tf-idf approach. In 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT). 2016. pp 61\u201366.","DOI":"10.1109\/ICEEOT.2016.7754750"},{"key":"4411_CR3","unstructured":"Bank D, Koenigstein N, Giryes R. Autoencoders. CoRR, 2020.https:\/\/arxiv.org\/abs\/2003.05991. Accessed 15 Apr 2025."},{"key":"4411_CR4","volume-title":"Pattern recognition and machine learning (information science and statistics)","author":"CM Bishop","year":"2006","unstructured":"Bishop CM. Pattern recognition and machine learning (information science and statistics). Berlin, Heidelberg: Springer-Verlag; 2006."},{"key":"4411_CR5","doi-asserted-by":"crossref","unstructured":"Cohan A, Feldman S, Beltagy I, Downey D, Weld DS. Specter: Document-level representation learning using citation-informed transformers, 2020.","DOI":"10.18653\/v1\/2020.acl-main.207"},{"key":"4411_CR6","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. CoRR, 2018.https:\/\/arxiv.org\/abs\/1810.04805. Accessed 15 Apr 2025."},{"key":"4411_CR7","doi-asserted-by":"crossref","unstructured":"Greene D, Cunningham P. Practical solutions to the problem of diagonal dominance in kernel document clustering. In Proc. 23rd International Conference on Machine learning (ICML\u201906). ACM Press, 2006. p. 377\u2013384","DOI":"10.1145\/1143844.1143892"},{"key":"4411_CR8","unstructured":"Grootendorst M. Bertopic: neural topic modeling with a class-based tf-idf procedure, 2022."},{"key":"4411_CR9","unstructured":"G\u00fcnther M, Mohr I, Wang B, Xiao H. Late chunking: Contextual chunk embeddings using long-context embedding models. arXiv preprint , 2024.https:\/\/arxiv.org\/abs\/2409.04701. Accessed 25 Mar 2025."},{"key":"4411_CR10","unstructured":"G\u00fcnther M, Ong J, Mohr I, Abdessalem A, Abel T, Akram MK, Guzman S, Mastrapas G, Sturua S, Wang B, Werk M, Wang N, Xiao H. Jina embeddings 2: 8192-token general-purpose text embeddings for long documents, 2024."},{"issue":"1","key":"4411_CR11","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF01908075","volume":"2","author":"L Hubert","year":"1985","unstructured":"Hubert L, Arabie P. Comparing partitions. J Classif. 1985;2(1):193\u2013218.","journal-title":"J Classif"},{"key":"4411_CR12","doi-asserted-by":"crossref","unstructured":"Jin X, Han J. K-Means Clustering. Boston, Springer. 2010. p. 563\u2013564","DOI":"10.1007\/978-0-387-30164-8_425"},{"issue":"1\u20132","key":"4411_CR13","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn HW. The hungarian method for the assignment problem. Naval Res Logist Q. 1955;2(1\u20132):83\u201397.","journal-title":"Naval Res Logist Q"},{"key":"4411_CR14","doi-asserted-by":"publisher","unstructured":"Lewis D. Reuters-21578 Text Categorization Collection. UCI Machine Learning Repository, 1987. https:\/\/doi.org\/10.24432\/C52G6M.","DOI":"10.24432\/C52G6M"},{"key":"4411_CR15","doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J, Melville J. UMAP: Uniform Manifold Approximation and Projection for dimension reduction. ArXiv e-prints, February 2018.","DOI":"10.21105\/joss.00861"},{"key":"4411_CR16","doi-asserted-by":"crossref","unstructured":"Qader WA, Ameen MM, Ahmed BI. An overview of bag of words;importance, implementation, applications, and challenges. In 2019 International Engineering Conference (IEC). 2019. p. 200\u2013204","DOI":"10.1109\/IEC47844.2019.8950616"},{"key":"4411_CR17","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I. Sentence-bert: Sentence embeddings using siamese bert-networks, 2019.","DOI":"10.18653\/v1\/D19-1410"},{"key":"4411_CR18","doi-asserted-by":"crossref","unstructured":"Rey D, Neuh\u00e4user M. Wilcoxon-signed-rank test. 2011. p. 1658\u20131659","DOI":"10.1007\/978-3-642-04898-2_616"},{"key":"4411_CR19","doi-asserted-by":"crossref","unstructured":"Douglas Reynolds. Gaussian mixture models. 2009. p. 659\u2013663","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"4411_CR20","unstructured":"Shlens J. A tutorial on principal component analysis. CoRR, 2014.https:\/\/arxiv.org\/abs\/1404.1100. Accessed 26 Mar 2025."},{"key":"4411_CR21","doi-asserted-by":"crossref","unstructured":"Tran Q-K, Pham N-K. Sboc: A segment-based bag of clusters approach for document clustering. In Nguyen Thai-Nghe, Thanh-Nghi Do, and Salem Benferhat, editors, Intelligent Systems and Data Science. Singapore, Springer Nature. 2025. p. 265\u2013279","DOI":"10.1007\/978-981-97-9613-7_20"},{"key":"4411_CR22","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I. Attention is all you need. CoRR, 2017.https:\/\/arxiv.org\/abs\/1706.03762. Accessed 14 May 2025."},{"key":"4411_CR23","first-page":"2837","volume":"11","author":"NX Vinh","year":"2010","unstructured":"Vinh NX, Epps J, Bailey J. Information theoretic measures for clusterings comparison: variants, properties, normalization and correction for chance. J Mach Learn Res. 2010;11:2837\u201354.","journal-title":"J Mach Learn Res"},{"key":"4411_CR24","doi-asserted-by":"crossref","unstructured":"Wang K, Reimers N, Gurevych I. Tsdae: Using transformer-based sequential denoising auto-encoder for unsupervised sentence embedding learning; 2021.","DOI":"10.18653\/v1\/2021.findings-emnlp.59"},{"key":"4411_CR25","doi-asserted-by":"crossref","unstructured":"Xu W, Liu X, Gong Y. Document clustering based on non-negative matrix factorization. In Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval, SIGIR \u201903, New York. Association for Computing Machinery. 2003. p. 267\u2013273.","DOI":"10.1145\/860435.860485"},{"key":"4411_CR26","unstructured":"Zhang X, Zhao JJ, LeCun Y. In NIPS: Character-level convolutional networks for text classification; Adv Neural Inf Process Syst. 2015. p. 267\u2013273."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04411-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04411-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04411-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T11:33:57Z","timestamp":1760355237000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04411-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":26,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["4411"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04411-5","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"12 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Research Involving Human and\/or Animals"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}}],"article-number":"897"}}