{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:20:40Z","timestamp":1784179240077,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["450330162"],"award-info":[{"award-number":["450330162"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["450330162"],"award-info":[{"award-number":["450330162"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnnls.2025.3538262","type":"journal-article","created":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T13:53:24Z","timestamp":1739973204000},"page":"14551-14565","source":"Crossref","is-referenced-by-count":10,"title":["Probabilistic Topic Modeling With Transformer Representations"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7837-7011","authenticated-orcid":false,"given":"Arik","family":"Reuter","sequence":"first","affiliation":[{"name":"Institute of Mathematics, Clausthal University of Technology, Clausthal-Zellerfeld, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton","family":"Thielmann","sequence":"additional","affiliation":[{"name":"Institute of Mathematics, Clausthal University of Technology, Clausthal-Zellerfeld, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0616-1027","authenticated-orcid":false,"given":"Christoph","family":"Weisser","sequence":"additional","affiliation":[{"name":"BASF, Ludwigshafen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"S\u00e4fken","sequence":"additional","affiliation":[{"name":"Institute of Mathematics, Clausthal University of Technology, Clausthal-Zellerfeld, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Kneib","sequence":"additional","affiliation":[{"name":"Chair of Statistics, Georg-August-Universität Göttingen, Göttingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref2","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1077"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00325"},{"key":"ref5","article-title":"Top2Vec: Distributed representations of topics","author":"Angelov","year":"2020","journal-title":"arXiv:2008.09470"},{"key":"ref6","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Mikolov"},{"key":"ref7","first-page":"1676","article-title":"Cross-lingual contextualized topic models with zero-shot learning","volume-title":"Proc. 16th Conf. Eur. Chapter Assoc. Comput. Linguistics","author":"Bianchi"},{"key":"ref8","article-title":"Pre-training is a hot topic: Contextualized document embeddings improve topic coherence","author":"Bianchi","year":"2020","journal-title":"arXiv:2004.03974"},{"key":"ref9","article-title":"Autoencoding variational inference for topic models","author":"Srivastava","year":"2017","journal-title":"arXiv:1703.01488"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007617005950"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOAS114"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623715"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/4728095"},{"key":"ref15","first-page":"4171","article-title":"BERT: Pre-training 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":"ref16","first-page":"1728","article-title":"Tired of topic models? Clusters of pretrained word embeddings make for fast and good topics too!","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP)","author":"Sia"},{"key":"ref17","article-title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","author":"Grootendorst","year":"2022","journal-title":"arXiv:2203.05794"},{"key":"ref18","article-title":"Topics in the haystack: Extracting and evaluating topics beyond coherence","author":"Thielmann","year":"2023","journal-title":"arXiv:2303.17324"},{"key":"ref19","first-page":"78","article-title":"An empirical evaluation of doc2vec with practical insights into document embedding generation","volume-title":"Proc. 1st Workshop Represent. Learn. NLP","author":"Lau"},{"key":"ref20","article-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv:1802.03426"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00205"},{"key":"ref22","first-page":"3982","article-title":"Sentence-BERT: Sentence embeddings using Siamese BERT-networks","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Reimers"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639726"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148204"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-015-0117-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref28","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020","journal-title":"arXiv:2003.10555"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/02664763.2021.1919063"},{"issue":"3","key":"ref30","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/S0019-9958(58)80003-0","article-title":"Dynamic programming and stochastic control processes","volume":"1","author":"Bellman","year":"1958","journal-title":"Inf. Control"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4314"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s10038-020-00851-4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-51935-3_34"},{"key":"ref34","article-title":"Text embeddings by weakly-supervised contrastive pre-training","author":"Wang","year":"2022","journal-title":"arXiv:2212.03533"},{"key":"ref35","first-page":"511","article-title":"Kernel topic models","volume-title":"Proc. Artif. Intell. Statist.","author":"Hennig"},{"key":"ref36","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015","journal-title":"arXiv:1505.00853"},{"key":"ref37","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Ioffe"},{"key":"ref38","volume-title":"Huggingface: All-MPNet-Base-v2","year":"2022"},{"key":"ref39","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref40","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NIPS","author":"Paszke"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref42","first-page":"1","article-title":"Understanding posterior collapse in generative latent variable models","volume-title":"Proc. DGS@ICLR","author":"Lucas"},{"key":"ref43","first-page":"100","article-title":"Automatic evaluation of topic coherence","volume-title":"Proc. Hum. Lang. Technol., Annu. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Newman"},{"key":"ref44","first-page":"2018","article-title":"Is automated topic model evaluation broken? The incoherence of coherence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hoyle"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.300"},{"key":"ref46","first-page":"2177","article-title":"Neural word embedding as implicit matrix factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Levy"},{"key":"ref47","first-page":"13","article-title":"Evaluating topic coherence using distributional semantics","volume-title":"Proc. 10th Int. Conf. Comput. Semantics","author":"Aletras"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-80599-9_4"},{"key":"ref49","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"13","author":"Lee"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1080\/01638539809545028"},{"key":"ref51","first-page":"1385","article-title":"Sharing clusters among related groups: Hierarchical Dirichlet processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"17","author":"Teh"},{"key":"ref52","first-page":"163","article-title":"Hidden topic Markov models","volume-title":"Proc. Artif. Intell. Statist.","author":"Gruber"},{"key":"ref53","first-page":"128","article-title":"Improving contextualized topic models with negative sampling","volume-title":"Proc. 19th Int. Conf. Natural Lang. Process. (ICON)","author":"Adhya"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.15"},{"key":"ref55","first-page":"1","article-title":"Neural topic model via optimal transport","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhao"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.176"},{"key":"ref57","first-page":"37335","article-title":"Effective neural topic modeling with embedding clustering regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-demos.31"},{"key":"ref60","first-page":"1","article-title":"Practical Bayesian optimization of machine learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Snoek"},{"key":"ref61","article-title":"Towards the TopMost: A topic modeling system toolkit","author":"Wu","year":"2023","journal-title":"arXiv:2309.06908"},{"key":"ref62","first-page":"435","article-title":"STREAM: Simplified topic retrieval, exploration, and analysis module","volume-title":"Proc. 62nd Annu. Meeting Assoc. Comput. Linguistics","author":"Thielmann"},{"key":"ref63","article-title":"Wasserstein auto-encoders","author":"Tolstikhin","year":"2017","journal-title":"arXiv:1711.01558"},{"key":"ref64","first-page":"1","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Higgins"},{"key":"ref65","first-page":"1532","article-title":"Glove: Global vectors for word representation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP)","author":"Pennington"},{"key":"ref66","article-title":"MTEB: Massive text embedding benchmark","author":"Muennighoff","year":"2022","journal-title":"arXiv:2210.07316"},{"key":"ref67","article-title":"Reuters-21578 text categorization collection data set","author":"Lewis","year":"1997"},{"key":"ref68","article-title":"Reading tea leaves: How humans interpret topic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"22","author":"Chang"},{"key":"ref69","volume-title":"Umap Package","author":"McInnes","year":"2018"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11114436\/10893705.pdf?arnumber=10893705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:01:16Z","timestamp":1754503276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10893705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":70,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3538262","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}