{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:45:17Z","timestamp":1771026317685,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":30,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543873.3587680","type":"proceedings-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T11:36:14Z","timestamp":1682681774000},"page":"1069-1076","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Self-supervised Pre-training and Semi-supervised Learning for Extractive Dialog Summarization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9420-7285","authenticated-orcid":false,"given":"Yingying","family":"Zhuang","sequence":"first","affiliation":[{"name":"Amazon, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1485-6566","authenticated-orcid":false,"given":"Jiecheng","family":"Song","sequence":"additional","affiliation":[{"name":"Amazon, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8738-9884","authenticated-orcid":false,"given":"Narayanan","family":"Sadagopan","sequence":"additional","affiliation":[{"name":"Amazon, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4445-3480","authenticated-orcid":false,"given":"Anurag","family":"Beniwal","sequence":"additional","affiliation":[{"name":"Amazon, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. Conversational-BERT. https:\/\/huggingface.co\/DeepPavlov\/bert-base-cased-conversational. Accessed: 2022-10-30."},{"key":"e_1_3_2_1_2_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew\u00a0E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_1_3_1","volume-title":"Self-training with few-shot rationalization: Teacher explanations aid student in few-shot nlu. arXiv preprint arXiv:2109.08259","author":"Bhat Meghana\u00a0Moorthy","year":"2021","unstructured":"Meghana\u00a0Moorthy Bhat, Alessandro Sordoni, and Subhabrata Mukherjee. 2021. Self-training with few-shot rationalization: Teacher explanations aid student in few-shot nlu. arXiv preprint arXiv:2109.08259 (2021)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9490"},{"key":"e_1_3_2_1_5_1","volume-title":"Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555","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_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.24"},{"key":"e_1_3_2_1_7_1","volume-title":"Dialogue discourse-aware graph model and data augmentation for meeting summarization. arXiv preprint arXiv:2012.03502","author":"Feng Xiachong","year":"2020","unstructured":"Xiachong Feng, Xiaocheng Feng, Bing Qin, and Xinwei Geng. 2020. Dialogue discourse-aware graph model and data augmentation for meeting summarization. arXiv preprint arXiv:2012.03502 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1443"},{"key":"e_1_3_2_1_9_1","volume-title":"MPC-BERT: A pre-trained language model for multi-party conversation understanding. arXiv preprint arXiv:2106.01541","author":"Gu Jia-Chen","year":"2021","unstructured":"Jia-Chen Gu, Chongyang Tao, Zhen-Hua Ling, Can Xu, Xiubo Geng, and Daxin Jiang. 2021. MPC-BERT: A pre-trained language model for multi-party conversation understanding. arXiv preprint arXiv:2106.01541 (2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99344-7_5"},{"key":"e_1_3_2_1_12_1","volume-title":"Revisiting self-training for neural sequence generation. arXiv preprint arXiv:1909.13788","author":"He Junxian","year":"2019","unstructured":"Junxian He, Jiatao Gu, Jiajun Shen, and Marc\u2019Aurelio Ranzato. 2019. Revisiting self-training for neural sequence generation. arXiv preprint arXiv:1909.13788 (2019)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of naacL-HLT. 4171\u20134186","author":"Ming-Wei\u00a0Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei\u00a0Chang Kenton and Lee\u00a0Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT. 4171\u20134186."},{"key":"e_1_3_2_1_14_1","volume-title":"Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451","author":"Kitaev Nikita","year":"2020","unstructured":"Nikita Kitaev, \u0141ukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451 (2020)."},{"key":"e_1_3_2_1_15_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_2_1_16_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74\u201381. https:\/\/aclanthology.org\/W04-1013"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"e_1_3_2_1_18_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_19_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.202"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10958"},{"key":"e_1_3_2_1_22_1","volume-title":"A deep reinforced model for abstractive summarization. arXiv preprint arXiv:1705.04304","author":"Paulus Romain","year":"2017","unstructured":"Romain Paulus, Caiming Xiong, and Richard Socher. 2017. A deep reinforced model for abstractive summarization. arXiv preprint arXiv:1705.04304 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"Language models are unsupervised multitask learners. OpenAI blog 1, 8","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a080)","author":"Ren Mengye","year":"2018","unstructured":"Mengye Ren, Wenyuan Zeng, Bin Yang, and Raquel Urtasun. 2018. Learning to Reweight Examples for Robust Deep Learning. In Proceedings of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a080), Jennifer Dy and Andreas Krause (Eds.). PMLR, 4334\u20134343. https:\/\/proceedings.mlr.press\/v80\/ren18a.html"},{"key":"e_1_3_2_1_25_1","volume-title":"Self-supervised learning for contextualized extractive summarization. arXiv preprint arXiv:1906.04466","author":"Wang Hong","year":"2019","unstructured":"Hong Wang, Xin Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, and William\u00a0Yang Wang. 2019. Self-supervised learning for contextualized extractive summarization. arXiv preprint arXiv:1906.04466 (2019)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"e_1_3_2_1_27_1","volume-title":"Adaptive self-training for few-shot neural sequence labeling. arXiv preprint arXiv:2010.03680","author":"Wang Yaqing","year":"2020","unstructured":"Yaqing Wang, Subhabrata Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, and Ahmed\u00a0Hassan Awadallah. 2020. Adaptive self-training for few-shot neural sequence labeling. arXiv preprint arXiv:2010.03680 (2020)."},{"key":"e_1_3_2_1_28_1","volume-title":"HIBERT: Document level pre-training of hierarchical bidirectional transformers for document summarization. arXiv preprint arXiv:1905.06566","author":"Zhang Xingxing","year":"2019","unstructured":"Xingxing Zhang, Furu Wei, and Ming Zhou. 2019. HIBERT: Document level pre-training of hierarchical bidirectional transformers for document summarization. arXiv preprint arXiv:1905.06566 (2019)."},{"key":"e_1_3_2_1_29_1","volume-title":"Neural document summarization by jointly learning to score and select sentences. arXiv preprint arXiv:1807.02305","author":"Zhou Qingyu","year":"2018","unstructured":"Qingyu Zhou, Nan Yang, Furu Wei, Shaohan Huang, Ming Zhou, and Tiejun Zhao. 2018. Neural document summarization by jointly learning to score and select sentences. arXiv preprint arXiv:1807.02305 (2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sigdial-1.54"}],"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":["Companion Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587680","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543873.3587680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:30:04Z","timestamp":1755819004000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587680"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":30,"alternative-id":["10.1145\/3543873.3587680","10.1145\/3543873"],"URL":"https:\/\/doi.org\/10.1145\/3543873.3587680","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"}}]}}