{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:32:08Z","timestamp":1793133128178,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-19-56151, IIS-17-41317, IIS 17-04532"],"award-info":[{"award-number":["IIS-19-56151, IIS-17-41317, IIS 17-04532"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute for Geospatial Understanding through an Integrative Discovery Environment (I-GUIDE)","award":["2118329"],"award-info":[{"award-number":["2118329"]}]},{"name":"Molecule Maker Lab Institute: An AI Research Institutes program","award":["2019897"],"award-info":[{"award-number":["2019897"]}]},{"name":"US DARPA KAIROS Program","award":["No. FA8750-19-2-1004"],"award-info":[{"award-number":["No. FA8750-19-2-1004"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["2021R1A6A3A14043765"],"award-info":[{"award-number":["2021R1A6A3A14043765"]}],"id":[{"id":"https:\/\/ror.org\/013aysd81","id-type":"ROR","asserted-by":"crossref"}]},{"name":"US DARPA INCAS Program","award":["No. HR001121C0165"],"award-info":[{"award-number":["No. HR001121C0165"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591782","type":"proceedings-article","created":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T20:22:23Z","timestamp":1689711743000},"page":"802-811","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5596-4972","authenticated-orcid":false,"given":"Susik","family":"Yoon","sequence":"first","affiliation":[{"name":"UIUC, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2173-3476","authenticated-orcid":false,"given":"Dongha","family":"Lee","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9790-4855","authenticated-orcid":false,"given":"Yunyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"UIUC, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3629-2696","authenticated-orcid":false,"given":"Jiawei","family":"Han","sequence":"additional","affiliation":[{"name":"UIUC, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3225644.3225842"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4573(02)00021-3"},{"key":"e_1_3_2_1_3_1","unstructured":"James Allan Jaime G Carbonell George Doddington Jonathan Yamron and Yiming Yang. 1998. Topic Detection and Tracking Pilot Study Final Report."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313396"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics and International Conference on Computational Linguistics.","author":"Bagga Amit","year":"1998","unstructured":"Amit Bagga and Breck Baldwin. 1998. Entity-based Cross-document Coreferencing using the Vector Space Model. In Proceedings of the Annual Meeting of the Association for Computational Linguistics and International Conference on Computational Linguistics."},{"key":"e_1_3_2_1_6_1","volume-title":"Scalable K-Means. Proceedings of the VLDB Endowment","volume":"5","author":"Bahmani Bahman","year":"2012","unstructured":"Bahman Bahmani, Benjamin Moseley, Andrea Vattani, Ravi Kumar, and Sergei Vassilvitskii. 2012. Scalable K-Means. Proceedings of the VLDB Endowment, Vol. 5, 7 (2012)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies."},{"key":"e_1_3_2_1_9_1","unstructured":"en_core_web_lg. 2023. https:\/\/spacy.io\/models\/en#en_core_web_lg"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407813"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.120"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006049"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2701"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Le Quoc","year":"2014","unstructured":"Quoc Le and Tomas Mikolov. 2014. Distributed Representations of Sentences and Documents. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512002"},{"key":"e_1_3_2_1_18_1","unstructured":"Dongha Lee Jiaming Shen Seonghyeon Lee Susik Yoon Hwanjo Yu and Jiawei Han. 2022b. TopicExpan: Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation. (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1058150.1058158"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the International Workshop on Narrative Extraction from Texts held in conjunction with the European Conference on Information Retrieval.","author":"Linger Mathis","year":"2020","unstructured":"Mathis Linger and Mhamed Hajaiej. 2020. Batch Clustering for Multilingual News Streaming. In Proceedings of the International Workshop on Narrative Extraction from Texts held in conjunction with the European Conference on Information Retrieval."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377939"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132852"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467392"},{"key":"e_1_3_2_1_25_1","volume-title":"Roberta: A Robustly Optimized Bert Pretraining approach. arXiv preprint arXiv:1907.11692","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_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010070"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.724"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1483"},{"key":"e_1_3_2_1_29_1","unstructured":"NBCNews. 2023. https:\/\/www.nbcnews.com\/news\/weather\/atmospheric-river-floods-northern-california-rcna63902"},{"key":"e_1_3_2_1_30_1","unstructured":"NewsAPI. 2023. https:\/\/newsapi.org"},{"key":"e_1_3_2_1_31_1","volume-title":"Sentence-t5: Scalable Sentence Encoders from Pre-trained Text-to-text Models. arXiv preprint arXiv:2108.08877","author":"Ni Jianmo","year":"2021","unstructured":"Jianmo Ni, Gustavo Hern\u00e1ndez \u00c1brego, Noah Constant, Ji Ma, Keith B Hall, Daniel Cer, and Yinfei Yang. 2021. Sentence-t5: Scalable Sentence Encoders from Pre-trained Text-to-text Models. arXiv preprint arXiv:2108.08877 (2021)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532046"},{"key":"e_1_3_2_1_33_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research, Vol. 21 (2020), 1--67.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4780"},{"key":"e_1_3_2_1_38_1","volume-title":"Simplifying Multilingual News Clustering Through Projection From a Shared Space. arXiv preprint arXiv:2204.13418","author":"Santos Jo","year":"2022","unstructured":"Jo ao Santos, Afonso Mendes, and Sebasti ao Miranda. 2022. Simplifying Multilingual News Clustering Through Projection From a Shared Space. arXiv preprint arXiv:2204.13418 (2022)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.198"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.135"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the International Workshop on Narrative Extraction from Texts held in conjunction with the European Conference on Information Retrieval.","author":"Staykovski Todor","year":"2019","unstructured":"Todor Staykovski, Alberto Barr\u00f3n-Cedeno, Giovanni Da San Martino, and Preslav Nakov. 2019. Dense vs. Sparse Representations for News Stream Clustering. In Proceedings of the International Workshop on Narrative Extraction from Texts held in conjunction with the European Conference on Information Retrieval."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/3339490.3339499"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of 15th Multiconference on Information Society. 221--224","author":"Trampuvs Mitja","year":"2012","unstructured":"Mitja Trampuvs and Blaz Novak. 2012. Internals of an aggregated web news feed. In Proceedings of 15th Multiconference on Information Society. 221--224."},{"key":"e_1_3_2_1_44_1","article-title":"Visualizing Data Using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing Data Using t-SNE. Journal of Machine Learning Research, Vol. 9, 11 (2008).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953024"},{"key":"e_1_3_2_1_46_1","unstructured":"Chuhan Wu Fangzhao Wu Yang Yu Tao Qi Yongfeng Huang and Qi Liu. 2021. NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application. In Findings of the Association for Computational Linguistics: EMNLP."},{"key":"e_1_3_2_1_47_1","volume-title":"Hou Pong Chan, and Jiawei Han","author":"Yoon Susik","year":"2023","unstructured":"Susik Yoon, Hou Pong Chan, and Jiawei Han. 2023. PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream. arXiv preprint arXiv:2302.05550 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342269"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403171"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539348"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452810"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539395"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591782","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3539618.3591782","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591782","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:37:58Z","timestamp":1750163878000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591782"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":52,"alternative-id":["10.1145\/3539618.3591782","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591782","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}