{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:46:40Z","timestamp":1787017600888,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"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, 2019897, 2118329"],"award-info":[{"award-number":["IIS-19-56151, IIS-17-41317, IIS 17-04532, 2019897, 2118329"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"US DARPA INCAS Program","award":["HR001121C0165"],"award-info":[{"award-number":["HR001121C0165"]}]},{"name":"US DARPA KAIROS Program","award":["FA8750-19-2-1004"],"award-info":[{"award-number":["FA8750-19-2-1004"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["2021R1A6A3A14043765"],"award-info":[{"award-number":["2021R1A6A3A14043765"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583507","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T19:30:25Z","timestamp":1682537425000},"page":"1853-1864","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["SCStory: Self-supervised and Continual Online Story Discovery"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5596-4972","authenticated-orcid":false,"given":"Susik","family":"Yoon","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2554-2888","authenticated-orcid":false,"given":"Yu","family":"Meng","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, 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, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3629-2696","authenticated-orcid":false,"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":[[2023,4,30]]},"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","volume-title":"Proceedings of the DARPA broadcast news transcription and understanding workshop.","author":"Allan James","year":"1998","unstructured":"James Allan, Jaime\u00a0G Carbonell, George Doddington, Jonathan Yamron, and Yiming Yang. 1998. Topic Detection and Tracking Pilot Study Final Report. In Proceedings of the DARPA broadcast news transcription and understanding workshop."},{"key":"e_1_3_2_1_3_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_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/2180912.2180915"},{"key":"e_1_3_2_1_5_1","volume-title":"Longformer: The Long-Document Transformer. arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew\u00a0E. Peters, and Arman Cohan. 2020. Longformer: The Long-Document Transformer. arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449834"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.194"},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5320-9"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"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":"10.1145\/3366423.3380247"},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Learning Representations.","author":"Gunel Beliz","year":"2021","unstructured":"Beliz Gunel, Jingfei Du, Alexis Conneau, and Ves Stoyanov. 2021. Supervised contrastive learning for pre-trained language model fine-tuning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","volume-title":"Augmenting Data with Mixup for Sentence Classification: An empirical study. arXiv preprint arXiv:1905.08941","author":"Guo Hongyu","year":"2019","unstructured":"Hongyu Guo, Yongyi Mao, and Richong Zhang. 2019. Augmenting Data with Mixup for Sentence Classification: An empirical study. arXiv preprint arXiv:1905.08941 (2019)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"e_1_3_2_1_16_1","volume-title":"Towards Continual Knowledge Learning of Language Models. In International Conference on Learning Representations.","author":"Jang Joel","year":"2021","unstructured":"Joel Jang, Seonghyeon Ye, Sohee Yang, Joongbo Shin, Janghoon Han, KIM Gyeonghun, Stanley\u00a0Jungkyu Choi, and Minjoon Seo. 2021. Towards Continual Knowledge Learning of Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.","author":"Jin Xisen","year":"2022","unstructured":"Xisen Jin, Dejiao Zhang, Henghui Zhu, Wei Xiao, Shang-Wen Li, Xiaokai Wei, Andrew Arnold, and Xiang Ren. 2022. Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora. 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_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006049"},{"key":"e_1_3_2_1_19_1","volume-title":"Adam: A Method for Stochastic Optimization. arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2577009"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2701"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512002"},{"key":"e_1_3_2_1_24_1","unstructured":"Dongha Lee Jiaming Shen Seonghyeon Lee Susik Yoon Hwanjo Yu and Jiawei Han. 2022. TopicExpan: Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation. (2022)."},{"key":"e_1_3_2_1_25_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_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377939"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132852"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467392"},{"key":"e_1_3_2_1_29_1","first-page":"23102","article-title":"Coco-lm: Correcting and Contrasting Text Sequences for Language Model Pretraining","volume":"34","author":"Meng Yu","year":"2021","unstructured":"Yu Meng, Chenyan Xiong, Payal Bajaj, Paul Bennett, Jiawei Han, Xia Song, 2021. Coco-lm: Correcting and Contrasting Text Sequences for Language Model Pretraining. Advances in Neural Information Processing Systems 34 (2021), 23102\u201323114.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1483"},{"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\u00a0Hern\u00e1ndez \u00c1brego, Noah Constant, Ji Ma, Keith\u00a0B 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":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.198"},{"key":"e_1_3_2_1_34_1","volume-title":"CEP-Wizard: Automatic Deployment of Distributed Complex Event Processing. In 2019 IEEE International Conference on Data Engineering (ICDE). IEEE","author":"Shin Yooju","year":"2019","unstructured":"Yooju Shin, Susik Yoon, Patara Trirat, and Jae-Gil Lee. 2019. CEP-Wizard: Automatic Deployment of Distributed Complex Event Processing. In 2019 IEEE International Conference on Data Engineering (ICDE). IEEE, 2004\u20132007."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522968.2522981"},{"key":"e_1_3_2_1_36_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\u00a0San\u00a0Martino, 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_37_1","volume-title":"Tacl: Improving BERT pre-training with token-aware contrastive learning. arXiv preprint arXiv:2111.04198","author":"Su Yixuan","year":"2021","unstructured":"Yixuan Su, Fangyu Liu, Zaiqiao Meng, Tian Lan, Lei Shu, Ehsan Shareghi, and Nigel Collier. 2021. Tacl: Improving BERT pre-training with token-aware contrastive learning. arXiv preprint arXiv:2111.04198 (2021)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.305"},{"key":"e_1_3_2_1_39_1","volume-title":"Representation Learning with Contrastive Predictive Coding. arXiv e-prints","author":"Oord Aaron Van\u00a0den","year":"2018","unstructured":"Aaron Van\u00a0den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. arXiv e-prints (2018), arXiv\u20131807."},{"key":"e_1_3_2_1_40_1","volume-title":"Visualizing Data Using t-SNE.Journal of Machine Learning Research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing Data Using t-SNE.Journal of Machine Learning Research 9, 11 (2008)."},{"key":"e_1_3_2_1_41_1","volume-title":"Attention is All You Need. Advances in Neural Information Processing Systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All You Need. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953024"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 9929\u20139939","author":"Wang Tongzhou","year":"2020","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere. In Proceedings of the International Conference on Machine Learning. PMLR, 9929\u20139939."},{"key":"e_1_3_2_1_44_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_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.331"},{"key":"e_1_3_2_1_46_1","volume-title":"Clear: Contrastive learning for sentence representation. arXiv preprint arXiv:2012.15466","author":"Wu Zhuofeng","year":"2020","unstructured":"Zhuofeng Wu, Sinong Wang, Jiatao Gu, Madian Khabsa, Fei Sun, and Hao Ma. 2020. Clear: Contrastive learning for sentence representation. arXiv preprint arXiv:2012.15466 (2020)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342269"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403171"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539348"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452810"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098027"},{"key":"e_1_3_2_1_52_1","volume-title":"International Conference on Learning Representations.","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann\u00a0N Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence. 3014\u20133021","author":"Zhou Deyu","year":"2016","unstructured":"Deyu Zhou, Haiyang Xu, Xin-Yu Dai, and Yulan He. 2016. Unsupervised Storyline Extraction from News Articles.. In Proceedings of the International Joint Conference on Artificial Intelligence. 3014\u20133021."}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583507","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3543507.3583507","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583507","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:47:02Z","timestamp":1750164422000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583507"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":53,"alternative-id":["10.1145\/3543507.3583507","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583507","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}