{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T06:23:22Z","timestamp":1792131802324,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-19-2-1004,W911NF-17-C-0099,HR001121C0165"],"award-info":[{"award-number":["FA8750-19-2-1004,W911NF-17-C-0099,HR001121C0165"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-19-56151,IIS-17-41317,IIS-17-04532,2019897"],"award-info":[{"award-number":["IIS-19-56151,IIS-17-41317,IIS-17-04532,2019897"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3485447.3512034","type":"proceedings-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T01:13:07Z","timestamp":1650849187000},"page":"3143-3152","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":43,"title":["Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations"],"prefix":"10.1145","author":[{"given":"Yu","family":"Meng","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Han","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,4,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Hagai Attias. 2000. A variational Bayesian framework for graphical models. NIPS."},{"key":"e_1_3_2_1_2_1","unstructured":"Arindam Banerjee Inderjit\u00a0S. Dhillon Joydeep Ghosh and Suvrit Sra. 2005. Clustering on the Unit Hypersphere using von Mises-Fisher Distributions. J. Mach. Learn. Res.(2005)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Kayhan Batmanghelich Ardavan Saeedi Karthik Narasimhan and Sam Gershman. 2016. Nonparametric spherical topic modeling with word embeddings. In ACL.","DOI":"10.18653\/v1\/P16-2087"},{"key":"e_1_3_2_1_4_1","volume-title":"A neural probabilistic language model. JMLR","author":"Bengio Yoshua","year":"2003","unstructured":"Yoshua Bengio, R\u00e9jean Ducharme, Pascal Vincent, and Christian Janvin. 2003. A neural probabilistic language model. JMLR (2003)."},{"key":"e_1_3_2_1_5_1","volume-title":"\u201cnearest neighbor","author":"Beyer Kevin","unstructured":"Kevin Beyer, Jonathan Goldstein, Raghu Ramakrishnan, and Uri Shaft. 1999. When is \u201cnearest neighbor\u201d meaningful?. In ICDT."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Federico Bianchi Silvia Terragni and Dirk Hovy. 2021. Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence. In ACL.","DOI":"10.18653\/v1\/2021.acl-short.96"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"David Blei and John Lafferty. 2006. Correlated topic models. In NIPS.","DOI":"10.1214\/07-AOAS114"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"David\u00a0M Blei and John\u00a0D Lafferty. 2006. Dynamic topic models. In ICML.","DOI":"10.1145\/1143844.1143859"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"David\u00a0M Blei John\u00a0D Lafferty 2007. A correlated topic model of science. The annals of applied statistics(2007).","DOI":"10.1214\/07-AOAS114"},{"key":"e_1_3_2_1_10_1","unstructured":"David\u00a0M Blei and Jon\u00a0D Mcauliffe. 2008. Supervised topic models. In NIPS."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"David\u00a0M. Blei Andrew\u00a0Y. Ng and Michael\u00a0I. Jordan. 2003. Latent Dirichlet Allocation. In NIPS.","DOI":"10.7551\/mitpress\/1120.003.0082"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197026.3197043"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Yatin Chaudhary Pankaj Gupta Khushbu Saxena Vivek Kulkarni Thomas\u00a0A. Runkler and Hinrich Sch\u00fctze. 2020. TopicBERT for Energy Efficient Document Classification. In EMNLP Findings.","DOI":"10.18653\/v1\/2020.findings-emnlp.152"},{"key":"e_1_3_2_1_14_1","volume-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555(2020).","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc\u00a0V Le, and Christopher\u00a0D Manning. 2020. ELECTRA: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555(2020)."},{"key":"e_1_3_2_1_15_1","unstructured":"Rajarshi Das Manzil Zaheer and Chris Dyer. 2015. Gaussian LDA for topic models with word embeddings. In ACL."},{"key":"e_1_3_2_1_16_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL."},{"key":"e_1_3_2_1_17_1","volume-title":"Topic modeling in embedding spaces. TACL","author":"Dieng B","year":"2020","unstructured":"Adji\u00a0B Dieng, Francisco\u00a0JR Ruiz, and David\u00a0M Blei. 2020. Topic modeling in embedding spaces. TACL (2020)."},{"key":"e_1_3_2_1_18_1","unstructured":"J.\u00a0R. Firth. 1957. A synopsis of linguistic theory 1930-55.(1957)."},{"key":"e_1_3_2_1_19_1","volume-title":"Anchored correlation explanation: Topic modeling with minimal domain knowledge. TACL","author":"Gallagher J","year":"2017","unstructured":"Ryan\u00a0J Gallagher, Kyle Reing, David Kale, and Greg Ver\u00a0Steeg. 2017. Anchored correlation explanation: Topic modeling with minimal domain knowledge. TACL (2017)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Samuel Gehman Suchin Gururangan Maarten Sap Yejin Choi and Noah\u00a0A. Smith. 2020. RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models. In EMNLP Findings.","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"e_1_3_2_1_21_1","unstructured":"Siddharth Gopal and Yiming Yang. 2014. Von Mises-Fisher Clustering Models. In ICML."},{"key":"e_1_3_2_1_22_1","unstructured":"Thomas\u00a0L Griffiths Michael\u00a0I Jordan Joshua\u00a0B Tenenbaum and David\u00a0M Blei. 2004. Hierarchical topic models and the nested Chinese restaurant process. In NIPS."},{"key":"e_1_3_2_1_23_1","unstructured":"Maarten Grootendorst. 2020. BERTopic: Leveraging BERT and c-TF-IDF to create easily interpretable topics. Zenodo: 10.5281\/zenodo.4430182(2020)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Pankaj Gupta Yatin Chaudhary and Hinrich Sch\u00fctze. 2021. Multi-source Neural Topic Modeling in Multi-view Embedding Spaces. In NAACL.","DOI":"10.18653\/v1\/2021.naacl-main.332"},{"key":"e_1_3_2_1_25_1","unstructured":"Geoffrey\u00a0E Hinton and Richard\u00a0S Zemel. 1993. Autoencoders Minimum Description Length and Helmholtz Free Energy. In NIPS."},{"key":"e_1_3_2_1_26_1","volume-title":"Latent semantic models for collaborative filtering. ACM TOIS","author":"Hofmann Thomas","year":"2004","unstructured":"Thomas Hofmann. 2004. Latent semantic models for collaborative filtering. ACM TOIS (2004)."},{"key":"e_1_3_2_1_27_1","volume-title":"Approximation capabilities of multilayer feedforward networks. Neural networks","author":"Hornik Kurt","year":"1991","unstructured":"Kurt Hornik. 1991. Approximation capabilities of multilayer feedforward networks. Neural networks (1991)."},{"key":"e_1_3_2_1_28_1","unstructured":"Alexander\u00a0Miserlis Hoyle Pranav Goel and Philip Resnik. 2020. Improving Neural Topic Models Using Knowledge Distillation. In EMNLP."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Jiaxin Huang Yu Meng Fang Guo Heng Ji and Jiawei Han. 2020. Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding. In EMNLP.","DOI":"10.18653\/v1\/2020.emnlp-main.568"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Jiaxin Huang Yiqing Xie Yu Meng Yunyi Zhang and Jiawei Han. 2020. CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring. In KDD.","DOI":"10.1145\/3394486.3403244"},{"key":"e_1_3_2_1_31_1","volume-title":"Adam: A method for stochastic optimization. In ICLR.","author":"Kingma P","year":"2015","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In ICLR."},{"key":"e_1_3_2_1_32_1","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114(2013)."},{"key":"e_1_3_2_1_33_1","unstructured":"Bohan Li Hao Zhou Junxian He Mingxuan Wang Yiming Yang and Lei Li. 2020. On the Sentence Embeddings from Pre-trained Language Models. In EMNLP."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Wei Li and Andrew McCallum. 2006. Pachinko allocation: DAG-structured mixture models of topic correlations. In ICML.","DOI":"10.1145\/1143844.1143917"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Yang Liu Zhiyuan Liu Tat-Seng Chua and Maosong Sun. 2015. Topical word embeddings. In AAAI.","DOI":"10.1609\/aaai.v29i1.9522"},{"key":"e_1_3_2_1_36_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019).","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"e_1_3_2_1_38_1","unstructured":"Xinyao Ma Maarten Sap Hannah Rashkin and Yejin Choi. 2020. PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction. In EMNLP."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Yu Meng Jiaxin Huang Guangyuan Wang Zihan Wang Chao Zhang Yu Zhang and Jiawei Han. 2020. Discriminative topic mining via category-name guided text embedding. In WWW.","DOI":"10.1145\/3366423.3380278"},{"key":"e_1_3_2_1_40_1","unstructured":"Yu Meng Jiaxin Huang Guangyuan Wang Chao Zhang Honglei Zhuang Lance\u00a0M. Kaplan and Jiawei Han. 2019. Spherical Text Embedding. In NeurIPS."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Yu Meng Jiaming Shen Chao Zhang and Jiawei Han. 2018. Weakly-Supervised Neural Text Classification. In CIKM.","DOI":"10.1145\/3269206.3271737"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Yu Meng Jiaming Shen Chao Zhang and Jiawei Han. 2019. Weakly-Supervised Hierarchical Text Classification. In AAAI.","DOI":"10.1145\/3269206.3271737"},{"key":"e_1_3_2_1_43_1","unstructured":"Yu Meng Chenyan Xiong Payal Bajaj Saurabh Tiwary Paul Bennett Jiawei Han and Xia Song. 2021. COCO-LM: Correcting and contrasting text sequences for language model pretraining. In NeurIPS."},{"key":"e_1_3_2_1_44_1","unstructured":"Yu Meng Chenyan Xiong Payal Bajaj Saurabh Tiwary Paul Bennett Jiawei Han and Xia Song. 2022. Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators. In ICLR."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Yu Meng Yunyi Zhang Jiaxin Huang Chenyan Xiong Heng Ji Chao Zhang and Jiawei Han. 2020. Text Classification Using Label Names Only: A Language Model Self-Training Approach. In EMNLP.","DOI":"10.18653\/v1\/2020.emnlp-main.724"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Yu Meng Yunyi Zhang Jiaxin Huang Yu Zhang Chao Zhang and Jiawei Han. 2020. Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding. In KDD.","DOI":"10.1145\/3394486.3403242"},{"key":"e_1_3_2_1_47_1","unstructured":"Yishu Miao Lei Yu and Phil Blunsom. 2016. Neural variational inference for text processing. In ICML."},{"key":"e_1_3_2_1_48_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Gregory\u00a0S. Corrado and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In NIPS."},{"key":"e_1_3_2_1_49_1","unstructured":"David Mimno Hanna Wallach Edmund Talley Miriam Leenders and Andrew McCallum. 2011. Optimizing semantic coherence in topic models. In EMNLP."},{"key":"e_1_3_2_1_50_1","unstructured":"Radford\u00a0M Neal. 1993. Probabilistic inference using Markov chain Monte Carlo methods."},{"key":"e_1_3_2_1_51_1","unstructured":"David Newman Jey\u00a0Han Lau Karl Grieser and Timothy Baldwin. 2010. Automatic evaluation of topic coherence. In NAACL."},{"key":"e_1_3_2_1_52_1","volume-title":"Improving topic models with latent feature word representations. TACL","author":"Nguyen Dat\u00a0Quoc","year":"2015","unstructured":"Dat\u00a0Quoc Nguyen, Richard Billingsley, Lan Du, and Mark Johnson. 2015. Improving topic models with latent feature word representations. TACL (2015)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Shrimai Prabhumoye Yulia Tsvetkov Ruslan Salakhutdinov and Alan\u00a0W. Black. 2018. Style Transfer Through Back-Translation. In ACL.","DOI":"10.18653\/v1\/P18-1080"},{"key":"e_1_3_2_1_54_1","unstructured":"Xipeng Qiu Tianxiang Sun Yige Xu Yunfan Shao Ning Dai and Xuanjing Huang. 2020. Pre-trained Models for Natural Language Processing: A Survey. arXiv preprint arXiv:2003.08271(2020)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Daniel Ramage David Hall Ramesh Nallapati and Christopher\u00a0D Manning. 2009. Labeled LDA: A supervised topic model for credit attribution in multi-labeled corpora. In EMNLP.","DOI":"10.3115\/1699510.1699543"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In EMNLP-IJCNLP.","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_57_1","unstructured":"Tim Salimans Diederik Kingma and Max Welling. 2015. Markov chain monte carlo and variational inference: Bridging the gap. In ICML."},{"key":"e_1_3_2_1_58_1","unstructured":"Evan Sandhaus. 2008. The New York Times Annotated Corpus."},{"key":"e_1_3_2_1_59_1","volume":"202","author":"Sia Suzanna","unstructured":"Suzanna Sia, Ayush Dalmia, and Sabrina\u00a0J Mielke. 2020. Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics Too!. In EMNLP.","journal-title":"J Mielke."},{"key":"e_1_3_2_1_60_1","unstructured":"Akash Srivastava and Charles Sutton. 2017. Autoencoding Variational Inference For Topic Models. In ICLR."},{"key":"e_1_3_2_1_61_1","unstructured":"Laure Thompson and David Mimno. 2020. Topic Modeling with Contextualized Word Representation Clusters. ArXiv abs\/2010.12626(2020)."},{"key":"e_1_3_2_1_62_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NIPS."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Dingding Wang Shenghuo Zhu Tao Li and Yihong Gong. 2009. Multi-document summarization using sentence-based topic models. In ACL.","DOI":"10.3115\/1667583.1667675"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"crossref","unstructured":"Rui Wang Xuemeng Hu Deyu Zhou Yulan He Yuxuan Xiong Chenchen Ye and Haiyang Xu. 2020. Neural Topic Modeling with Bidirectional Adversarial Training. In ACL.","DOI":"10.18653\/v1\/2020.acl-main.32"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Xuerui Wang Andrew McCallum and Xing Wei. 2007. Topical n-grams: Phrase and topic discovery with an application to information retrieval. In ICDM.","DOI":"10.1109\/ICDM.2007.86"},{"key":"e_1_3_2_1_66_1","unstructured":"Junyuan Xie Ross Girshick and Ali Farhadi. 2016. Unsupervised deep embedding for clustering analysis. In ICML."},{"key":"e_1_3_2_1_67_1","unstructured":"Zhilin Yang Zihang Dai Yiming Yang Jaime Carbonell Russ\u00a0R Salakhutdinov and Quoc\u00a0V Le. 2019. XLNet: Generalized Autoregressive Pretraining for Language Understanding. In NeurIPS."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Yu Zhang Shweta Garg Yu Meng Xiusi Chen and Jiawei Han. 2022. MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information. In WSDM.","DOI":"10.1145\/3488560.3498384"}],"event":{"name":"WWW '22: The ACM Web Conference 2022","location":"Virtual Event, Lyon France","acronym":"WWW '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2022"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3512034","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485447.3512034","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485447.3512034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T15:30:06Z","timestamp":1750174206000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3512034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":68,"alternative-id":["10.1145\/3485447.3512034","10.1145\/3485447"],"URL":"https:\/\/doi.org\/10.1145\/3485447.3512034","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-04-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}