{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T16:41:25Z","timestamp":1765557685863,"version":"3.48.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007224","name":"NAFOSTED","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007224","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.knosys.2025.114762","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T01:36:34Z","timestamp":1761788194000},"page":"114762","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Sub-document neural topic model"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3535-1242","authenticated-orcid":false,"given":"Tung","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3511-5591","authenticated-orcid":false,"given":"Duy-Tung","family":"Doan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huu-Thanh","family":"Luong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0011-5137","authenticated-orcid":false,"given":"Linh","family":"Ngo Van","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2025.114762_bib0001","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2025.114762_bib0002","series-title":"International Conference on Learning Representations","article-title":"Autoencoding variational inference for topic models","author":"Srivastava","year":"2017"},{"key":"10.1016\/j.knosys.2025.114762_bib0003","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"13528","article-title":"Topic modeling: contextual token embeddings are all you need","author":"Angelov","year":"2024"},{"issue":"2","key":"10.1016\/j.knosys.2025.114762_bib0004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10462-023-10661-7","article-title":"A survey on neural topic models: methods, applications, and challenges","volume":"57","author":"Wu","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.knosys.2025.114762_bib0005","series-title":"2Nd International Conference on Learning Representations, ICLR 2014","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"10.1016\/j.knosys.2025.114762_bib0006","article-title":"Top2vec: distributed representations of topics","volume":"abs\/2008.09470","author":"Angelov","year":"2020","journal-title":"CoRR"},{"year":"2022","series-title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","author":"Grootendorst","key":"10.1016\/j.knosys.2025.114762_bib0007"},{"key":"10.1016\/j.knosys.2025.114762_bib0008","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1162\/tacl_a_00325","article-title":"Topic modeling in embedding spaces","volume":"8","author":"Dieng","year":"2020","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"10.1016\/j.knosys.2025.114762_bib0009","series-title":"ACL-IJCNLP (Volume 2: Short Papers)","first-page":"759","article-title":"Pre-training is a hot topic: contextualized document embeddings improve topic coherence","author":"Bianchi","year":"2021"},{"key":"10.1016\/j.knosys.2025.114762_bib0010","series-title":"International Conference on Machine Learning","first-page":"37335","article-title":"Effective neural topic modeling with embedding clustering regularization","author":"Wu","year":"2023"},{"key":"10.1016\/j.knosys.2025.114762_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130420","article-title":"A framework for neural topic modeling with mutual information and group regularization","volume":"645","author":"Nguyen","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2025.114762_bib0012","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"6171","article-title":"GINOpic: topic modeling with graph isomorphism network","author":"Adhya","year":"2024"},{"key":"10.1016\/j.knosys.2025.114762_bib0013","series-title":"Proceedings of the 4Th Workshop on Computational Approaches to Discourse (CODI 2023)","first-page":"106","article-title":"SAE-NTM: Sentence-Aware encoder for neural topic modeling","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2025.114762_bib0014","series-title":"Proceedings of the 17Th Conference of the European Chapter of the Association for Computational Linguistics","first-page":"1802","article-title":"Unified neural topic model via contrastive learning and term weighting","author":"Han","year":"2023"},{"key":"10.1016\/j.knosys.2025.114762_bib0015","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12\u201316, 2024","first-page":"7758","article-title":"Neuromax: enhancing neural topic modeling via maximizing mutual information and group topic regularization","author":"Pham","year":"2024"},{"issue":"4","key":"10.1016\/j.knosys.2025.114762_bib0016","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1145\/2133806.2133826","article-title":"Probabilistic topic models","volume":"55","author":"Blei","year":"2012","journal-title":"Commun. ACM"},{"key":"10.1016\/j.knosys.2025.114762_bib0017","series-title":"Advances in Neural Information Processing Systems","article-title":"Algorithms for non-negative matrix factorization","volume":"13","author":"Lee","year":"2000"},{"key":"10.1016\/j.knosys.2025.114762_bib0018","series-title":"Proceedings of the 21Th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"567-576","article-title":"Simultaneous Discovery of Common and Discriminative Topics via Joint Nonnegative Matrix Factorization","author":"Kim","year":"2015"},{"key":"10.1016\/j.knosys.2025.114762_bib0019","series-title":"Advances in Knowledge Discovery and Data Mining","first-page":"247","article-title":"Keeping priors in streaming bayesian learning","author":"Duc","year":"2017"},{"key":"10.1016\/j.knosys.2025.114762_bib0020","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.neucom.2021.10.047","article-title":"A graph convolutional topic model for short and noisy text streams","volume":"468","author":"Van Linh","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2025.114762_bib0021","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.neucom.2022.07.019","article-title":"Balancing stability and plasticity when learning topic models from short and noisy text streams","volume":"505","author":"Nguyen","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2025.114762_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128757","article-title":"Out-of-vocabulary handling and topic quality control strategies in streaming topic models","volume":"614","author":"Nguyen","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2025.114762_bib0023","series-title":"Proceedings of the ACL-IJCNLP 2009 Conference Short Papers","first-page":"297","article-title":"Multi-Document summarization using sentence-based topic models","author":"Wang","year":"2009"},{"key":"10.1016\/j.knosys.2025.114762_bib0024","series-title":"Proceedings of the 39Th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2016, Pisa, Italy, July 17\u201321, 2016","first-page":"921","article-title":"On a topic model for sentences","author":"Balikas","year":"2016"},{"key":"10.1016\/j.knosys.2025.114762_bib0025","series-title":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4\u20139, 2017, San Francisco, California, USA","first-page":"3223","article-title":"Recurrent attentional topic model","author":"Li","year":"2017"},{"issue":"6","key":"10.1016\/j.knosys.2025.114762_bib0026","doi-asserted-by":"crossref","first-page":"2545","DOI":"10.1007\/s11280-018-0639-1","article-title":"Sentence level topic models for associated topics extraction","volume":"22","author":"Jiang","year":"2019","journal-title":"World Wide Web"},{"key":"10.1016\/j.knosys.2025.114762_bib0027","series-title":"9Th International Conference on Learning Representations, ICLR 2021","article-title":"Neural topic model via optimal transport","author":"Zhao","year":"2021"},{"key":"10.1016\/j.knosys.2025.114762_bib0028","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022","article-title":"Representing mixtures of word embeddings with mixtures of topic embeddings","author":"Wang","year":"2022"},{"key":"10.1016\/j.knosys.2025.114762_bib0029","series-title":"Proceedings of the 16Th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume","first-page":"1676","article-title":"Cross-lingual contextualized topic models with zero-shot learning","author":"Bianchi","year":"2021"},{"key":"10.1016\/j.knosys.2025.114762_bib0030","series-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"4507","article-title":"Sharpness-Aware minimization for topic models with high-Quality document representations","author":"Nguyen","year":"2025"},{"key":"10.1016\/j.knosys.2025.114762_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131268","article-title":"TopiCOT: neural topic model aligning with pre-trained clustering and optimal transport","volume":"654","author":"Nguyen","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2025.114762_bib0032","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"19261","article-title":"On the affinity, rationality, and diversity of hierarchical topic modeling","volume":"38","author":"Wu","year":"2024"},{"key":"10.1016\/j.knosys.2025.114762_bib0033","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"5916","article-title":"Dynamic structured neural topic model with self-Attention mechanism","author":"Miyamoto","year":"2023"},{"key":"10.1016\/j.knosys.2025.114762_bib0034","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"3088","article-title":"Modeling dynamic topics in chain-Free fashion by evolution-Tracking contrastive learning and unassociated word exclusion","author":"Wu","year":"2024"},{"key":"10.1016\/j.knosys.2025.114762_bib0035","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1772","article-title":"Short text topic modeling with topic distribution quantization and negative sampling decoder","author":"Wu","year":"2020"},{"key":"10.1016\/j.knosys.2025.114762_bib0036","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"2748","article-title":"Mitigating data sparsity for short text topic modeling by topic-Semantic contrastive learning","author":"Wu","year":"2022"},{"key":"10.1016\/j.knosys.2025.114762_bib0037","series-title":"Proceedings of the 62Nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","first-page":"21","article-title":"Topic modeling for short texts with large language models","author":"Doi","year":"2024"},{"key":"10.1016\/j.knosys.2025.114762_bib0038","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"13762","article-title":"Combating label sparsity in short text topic modeling via nearest neighbor augmentation","author":"Lin","year":"2024"},{"key":"10.1016\/j.knosys.2025.114762_bib0039","article-title":"Topic modeling with contextualized word representation clusters","volume":"abs\/2010.12626","author":"Thompson","year":"2020","journal-title":"CoRR"},{"key":"10.1016\/j.knosys.2025.114762_bib0040","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1728","article-title":"Tired of topic models? clusters of pretrained word embeddings make for fast and good topics too!","author":"Sia","year":"2020"},{"key":"10.1016\/j.knosys.2025.114762_bib0041","series-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"7548","article-title":"CAST: Corpus-Aware self-similarity enhanced topic modelling","author":"Ma","year":"2025"},{"key":"10.1016\/j.knosys.2025.114762_bib0042","series-title":"Advances in Neural Information Processing Systems","article-title":"FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm","author":"Wu","year":"2024"},{"key":"10.1016\/j.knosys.2025.114762_bib0043","series-title":"2023 IEEE International Conference on Big Data (BigData)","first-page":"1236","article-title":"Prompting Large Language Models for Topic Modeling","author":"Wang","year":"2023"},{"key":"10.1016\/j.knosys.2025.114762_bib0044","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"2956","article-title":"TopicGPT: a prompt-based topic modeling framework","author":"Pham","year":"2024"},{"key":"10.1016\/j.knosys.2025.114762_bib0045","series-title":"Proceedings of the 29Th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12\u201317, 2022","first-page":"4037","article-title":"Multilingual and multimodal topic modelling with pretrained embeddings","author":"Zosa","year":"2022"},{"key":"10.1016\/j.knosys.2025.114762_bib0046","series-title":"Proceedings of the 28Th ACM International Conference on Information and Knowledge Management, CIKM 2019, Beijing, China, November 3\u20137, 2019","first-page":"1071","article-title":"Federated topic modeling","author":"Jiang","year":"2019"},{"key":"10.1016\/j.knosys.2025.114762_bib0047","series-title":"Machine Learning Proceedings 1995","first-page":"331","article-title":"NewsWeeder: Learning to Filter Netnews","author":"Lang","year":"1995"},{"key":"10.1016\/j.knosys.2025.114762_bib0048","first-page":"364","article-title":"HDLTex: Hierarchical Deep Learning for Text Classification","author":"Kowsari","year":"2017"},{"key":"10.1016\/j.knosys.2025.114762_bib0049","series-title":"Proceedings of the 23Rd International Conference on Machine Learning","first-page":"377","article-title":"Practical solutions to the problem of diagonal dominance in kernel document clustering","author":"Greene","year":"2006"},{"key":"10.1016\/j.knosys.2025.114762_bib0050","series-title":"Proceedings of the 62Nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","first-page":"31","article-title":"Towards the topmost: a topic modeling system toolkit","author":"Wu","year":"2024"},{"key":"10.1016\/j.knosys.2025.114762_bib0051","series-title":"Proceedings of the Eighth ACM International Conference on Web Search and Data Mining","first-page":"399-408","article-title":"Exploring the space of topic coherence measures","author":"R\u00f6der","year":"2015"},{"year":"2008","series-title":"Introduction to Information Retrieval","author":"Manning","key":"10.1016\/j.knosys.2025.114762_bib0052"},{"key":"10.1016\/j.knosys.2025.114762_bib0053","first-page":"9348","article-title":"Revisiting Automated Topic Model Evaluation with Large Language Models","author":"Stammbach","year":"2023"},{"key":"10.1016\/j.knosys.2025.114762_bib0054","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1532","article-title":"Glove: global vectors for word representation","author":"Pennington","year":"2014"},{"key":"10.1016\/j.knosys.2025.114762_bib0055","article-title":"GPT-4 Technical report","volume":"abs\/2303.08774","author":"OpenAI","year":"2023","journal-title":"CoRR"},{"key":"10.1016\/j.knosys.2025.114762_bib0056","series-title":"Proceedings of the 17Th Conference of the European Chapter of the Association for Computational Linguistics","first-page":"2220","article-title":"Do neural topic models really need dropout? analysis of the effect of dropout in topic modeling","author":"Adhya","year":"2023"},{"issue":"4","key":"10.1016\/j.knosys.2025.114762_bib0057","doi-asserted-by":"crossref","DOI":"10.1145\/1852102.1852106","article-title":"A similarity measure for indefinite rankings","volume":"28","author":"Webber","year":"2010","journal-title":"ACM Trans. Inf. Syst."},{"issue":"5\u20136","key":"10.1016\/j.knosys.2025.114762_bib0058","first-page":"355","article-title":"Computational optimal transport","volume":"11","author":"Peyr\u00e9","year":"2018","journal-title":"Found. Trends Mach. Learn."},{"key":"10.1016\/j.knosys.2025.114762_bib0059","series-title":"Advances in Neural Information Processing Systems","article-title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transport","author":"Cuturi","year":"2013"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705125018003?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705125018003?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T16:27:28Z","timestamp":1765556848000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705125018003"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":59,"alternative-id":["S0950705125018003"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2025.114762","relation":{},"ISSN":["0950-7051"],"issn-type":[{"type":"print","value":"0950-7051"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Sub-document neural topic model","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2025.114762","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114762"}}