{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:51:44Z","timestamp":1779306704997,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"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":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599830","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:13:58Z","timestamp":1691172838000},"page":"3724-3736","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Fusing Multimodal Signals on Hyper-complex Space for Extreme Abstractive Text Summarization (TL;DR) of Scientific Contents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4992-0505","authenticated-orcid":false,"given":"Yash Kumar","family":"Atri","sequence":"first","affiliation":[{"name":"IIIT Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0769-6381","authenticated-orcid":false,"given":"Vikram","family":"Goyal","sequence":"additional","affiliation":[{"name":"IIIT Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0210-0369","authenticated-orcid":false,"given":"Tanmoy","family":"Chakraborty","sequence":"additional","affiliation":[{"name":"IIIT Delhi, Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107152"},{"key":"e_1_3_2_2_2_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2015 . Neural Machine Translation by Jointly Learning to Align and Translate . In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409 .0473 Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.0473"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/lnc3.12170"},{"key":"e_1_3_2_2_4_1","volume-title":"Longformer: The Long-Document Transformer. arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy , Matthew E. Peters , and Arman Cohan . 2020 . Longformer: The Long-Document Transformer. arXiv:2004.05150 (2020). Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. Longformer: The Long-Document Transformer. arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_2_5_1","first-page":"428","volume-title":"TLDR: Extreme Summarization of Scientific Documents. In Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Cachola Isabel","year":"2020","unstructured":"Isabel Cachola , Kyle Lo , Arman Cohan , and Daniel Weld . 2020 . TLDR: Extreme Summarization of Scientific Documents. In Findings of the Association for Computational Linguistics: EMNLP 2020 . Association for Computational Linguistics, Online, 4766--4777. https:\/\/doi.org\/10. 18653\/v1\/2020.findings-emnlp. 428 10.18653\/v1 Isabel Cachola, Kyle Lo, Arman Cohan, and Daniel Weld. 2020. TLDR: Extreme Summarization of Scientific Documents. In Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, Online, 4766--4777. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.428"},{"key":"e_1_3_2_2_6_1","first-page":"2","article-title":"The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries","volume":"51","author":"Carbinell Jaime","year":"2017","unstructured":"Jaime Carbinell and Jade Goldstein . 2017 . The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries . SIGIR Forum , Vol. 51 , 2 (Aug. 2017), 209--210. https:\/\/doi.org\/10.1145\/3130348.3130369 10.1145\/3130348.3130369 Jaime Carbinell and Jade Goldstein. 2017. The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries. SIGIR Forum, Vol. 51, 2 (Aug. 2017), 209--210. https:\/\/doi.org\/10.1145\/3130348.3130369","journal-title":"SIGIR Forum"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1438"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1046"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/514"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105363"},{"key":"e_1_3_2_2_11_1","first-page":"19","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the ACL: Human Language Technologies","volume":"1","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 Proceedings of the 2019 Conference of the North American Chapter of the ACL: Human Language Technologies , Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. https:\/\/doi.org\/10. 18653\/v1\/N 19 - 1423 10.18653\/v1 Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the ACL: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. https:\/\/doi.org\/10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2902507"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1523"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1102"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1443"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1117"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2019.02.003"},{"key":"e_1_3_2_2_18_1","volume-title":"The ICSI Summarization System at TAC","author":"Gillick Daniel","year":"2008","unstructured":"Daniel Gillick , Benoit Favre , and Dilek Hakkani-T\u00fcr . 2008. The ICSI Summarization System at TAC 2008 .. In Tac . Daniel Gillick, Benoit Favre, and Dilek Hakkani-T\u00fcr. 2008. The ICSI Summarization System at TAC 2008.. In Tac."},{"key":"e_1_3_2_2_19_1","volume-title":"Audio Summarization with Audio Features and Probability Distribution Divergence. ArXiv","author":"Gonz'alez-Gallardo Carlos-Emiliano","year":"2020","unstructured":"Carlos-Emiliano Gonz'alez-Gallardo , Romain Deveaud , Eric SanJuan , and Juan-Manuel Torres . 2020. Audio Summarization with Audio Features and Probability Distribution Divergence. ArXiv , Vol. abs\/ 2001 .07098 ( 2020 ). Carlos-Emiliano Gonz'alez-Gallardo, Romain Deveaud, Eric SanJuan, and Juan-Manuel Torres. 2020. Audio Summarization with Audio Features and Probability Distribution Divergence. ArXiv, Vol. abs\/2001.07098 (2020)."},{"key":"e_1_3_2_2_20_1","volume-title":"Sustainable Advanced Computing","author":"Gupta Anushka","unstructured":"Anushka Gupta , Diksha Chugh , Anjum, and Rahul Katarya . 2022. Automated News Summarization Using Transformers . In Sustainable Advanced Computing , Sagaya Aurelia, Somashekhar S. Hiremath, Karthikeyan Subramanian, and Saroj Kr. Biswas (Eds.). Springer Singapore , Singapore , 249--259. Anushka Gupta, Diksha Chugh, Anjum, and Rahul Katarya. 2022. Automated News Summarization Using Transformers. In Sustainable Advanced Computing, Sagaya Aurelia, Somashekhar S. Hiremath, Karthikeyan Subramanian, and Saroj Kr. Biswas (Eds.). Springer Singapore, Singapore, 249--259."},{"key":"e_1_3_2_2_21_1","unstructured":"Karl Moritz Hermann Tomas Kocisky Edward Grefenstette Lasse Espeholt Will Kay Mustafa Suleyman and Phil Blunsom. 2015. Teaching machines to read and comprehend. In Advances in neural information processing systems. 1693--1701.  Karl Moritz Hermann Tomas Kocisky Edward Grefenstette Lasse Espeholt Will Kay Mustafa Suleyman and Phil Blunsom. 2015. Teaching machines to read and comprehend. In Advances in neural information processing systems. 1693--1701."},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings of the IEEE\/CVF Conference on CVPR Workshops. 958--959","author":"Iashin Vladimir","year":"2020","unstructured":"Vladimir Iashin and Esa Rahtu . 2020 . Multi-modal Dense Video Captioning . In Proceedings of the IEEE\/CVF Conference on CVPR Workshops. 958--959 . Vladimir Iashin and Esa Rahtu. 2020. Multi-modal Dense Video Captioning. In Proceedings of the IEEE\/CVF Conference on CVPR Workshops. 958--959."},{"key":"e_1_3_2_2_23_1","volume-title":"Springer Berlin Heidelberg","author":"Joyce James M.","unstructured":"James M. Joyce . 2011. Kullback-Leibler Divergence . Springer Berlin Heidelberg , Berlin, Heidelberg , 720--722. https:\/\/doi.org\/10.1007\/978-3-642-04898-2_327 10.1007\/978-3-642-04898-2_327 James M. Joyce. 2011. Kullback-Leibler Divergence. Springer Berlin Heidelberg, Berlin, Heidelberg, 720--722. https:\/\/doi.org\/10.1007\/978-3-642-04898-2_327"},{"key":"e_1_3_2_2_24_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev etal 2017. The kinetics human action video dataset. CoRR (2017).  Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. CoRR (2017)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1446"},{"key":"e_1_3_2_2_27_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis , Yinhan Liu , Naman Goyal , Marjan Ghazvininejad , Abdelrahman Mohamed , Omer Levy , Ves Stoyanov , and Luke Zettlemoyer . 2019 . Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019). Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/577"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2848260"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2856058"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2031"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463111"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.144"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240667"},{"key":"e_1_3_2_2_35_1","volume-title":"Fine-tune BERT for extractive summarization. arXiv preprint arXiv:1903.10318","author":"Liu Yang","year":"2019","unstructured":"Yang Liu . 2019. Fine-tune BERT for extractive summarization. arXiv preprint arXiv:1903.10318 ( 2019 ). Yang Liu. 2019. Fine-tune BERT for extractive summarization. arXiv preprint arXiv:1903.10318 (2019)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.447"},{"key":"#cr-split#-e_1_3_2_2_37_1.1","doi-asserted-by":"crossref","unstructured":"Yuning Mao Ming Zhong and Jiawei Han. 2022. CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision. https:\/\/doi.org\/10.48550\/ARXIV.2205.06207 10.48550\/ARXIV.2205.06207","DOI":"10.18653\/v1\/2022.emnlp-main.750"},{"key":"#cr-split#-e_1_3_2_2_37_1.2","doi-asserted-by":"crossref","unstructured":"Yuning Mao Ming Zhong and Jiawei Han. 2022. CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision. https:\/\/doi.org\/10.48550\/ARXIV.2205.06207","DOI":"10.18653\/v1\/2022.emnlp-main.750"},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of the 2004 Conference on EMNLP. ACL","author":"Mihalcea Rada","year":"2004","unstructured":"Rada Mihalcea and Paul Tarau . 2004 . TextRank: Bringing Order into Text . In Proceedings of the 2004 Conference on EMNLP. ACL , Barcelona, Spain, 404--411. https:\/\/www.aclweb.org\/anthology\/W04-3252 Rada Mihalcea and Paul Tarau. 2004. TextRank: Bringing Order into Text. In Proceedings of the 2004 Conference on EMNLP. ACL, Barcelona, Spain, 404--411. https:\/\/www.aclweb.org\/anthology\/W04-3252"},{"key":"e_1_3_2_2_39_1","unstructured":"Jonghwan Mun Minsu Cho and Bohyung Han. 2017. Text-guided Attention Model for Image Captioning. In AAAI. 4233--4239.  Jonghwan Mun Minsu Cho and Bohyung Han. 2017. Text-guided Attention Model for Image Captioning. In AAAI. 4233--4239."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10958"},{"key":"e_1_3_2_2_41_1","first-page":"16","volume-title":"Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning. ACL","author":"Nallapati Ramesh","year":"1865","unstructured":"Ramesh Nallapati , Bowen Zhou , Cicero dos Santos , cC aug lar Gu\u00cc?lcc ehre, and Bing Xiang. 2016. Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond . In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning. ACL , Berlin, Germany, 280--290. https:\/\/doi.org\/10. 1865 3\/v1\/K 16 - 1028 10.18653\/v1 Ramesh Nallapati, Bowen Zhou, Cicero dos Santos, cC aug lar Gu\u00cc?lcc ehre, and Bing Xiang. 2016. Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond. In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning. ACL, Berlin, Germany, 280--290. https:\/\/doi.org\/10.18653\/v1\/K16-1028"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1659"},{"key":"e_1_3_2_2_43_1","volume-title":"MHMS: Multimodal Hierarchical Multimedia Summarization. https:\/\/doi.org\/10.48550\/ARXIV.2204.03734","author":"Qiu Jielin","year":"2022","unstructured":"Jielin Qiu , Jiacheng Zhu , Mengdi Xu , Franck Dernoncourt , Trung Bui , Zhaowen Wang , Bo Li , Ding Zhao , and Hailin Jin . 2022 . MHMS: Multimodal Hierarchical Multimedia Summarization. https:\/\/doi.org\/10.48550\/ARXIV.2204.03734 10.48550\/ARXIV.2204.03734 Jielin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, and Hailin Jin. 2022. MHMS: Multimodal Hierarchical Multimedia Summarization. https:\/\/doi.org\/10.48550\/ARXIV.2204.03734"},{"key":"e_1_3_2_2_44_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 , 140 (2020), 1 -- 67 . http:\/\/jmlr.org\/papers\/v21\/20-074.html 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, 140 (2020), 1--67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_45_1","first-page":"1","article-title":"How2: A Large-scale Dataset For Multimodal Language Understanding. In Proceedings of the Workshop on Visually Grounded Interaction and Language (ViGIL)","volume":"26","author":"Sanabria Ramon","year":"2018","unstructured":"Ramon Sanabria , Ozan Caglayan , Shruti Palaskar , Desmond Elliott , Lo\u00efc Barrault , Lucia Specia , and Florian Metze . 2018 . How2: A Large-scale Dataset For Multimodal Language Understanding. In Proceedings of the Workshop on Visually Grounded Interaction and Language (ViGIL) . NeurIPS , 26 . 1 -- 26 .12. http:\/\/arxiv.org\/abs\/1811.00347 Ramon Sanabria, Ozan Caglayan, Shruti Palaskar, Desmond Elliott, Lo\u00efc Barrault, Lucia Specia, and Florian Metze. 2018. How2: A Large-scale Dataset For Multimodal Language Understanding. In Proceedings of the Workshop on Visually Grounded Interaction and Language (ViGIL). NeurIPS, 26.1--26.12. http:\/\/arxiv.org\/abs\/1811.00347","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). ACL","author":"Liu Peter J.","year":"1865","unstructured":"Abigail See, Peter J. Liu , and Christopher D. Manning . 2017. Get To The Point: Summarization with Pointer-Generator Networks . In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). ACL , Vancouver, Canada, 1073--1083. https:\/\/doi.org\/10. 1865 3\/v1\/P17--1099 10.18653\/v1 Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get To The Point: Summarization with Pointer-Generator Networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). ACL, Vancouver, Canada, 1073--1083. https:\/\/doi.org\/10.18653\/v1\/P17--1099"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.05.022"},{"key":"e_1_3_2_2_48_1","volume-title":"Remote sensing image captioning via Variational Autoencoder and Reinforcement Learning. Knowledge-Based Systems","author":"Shen Xiangqing","year":"2020","unstructured":"Xiangqing Shen , Bing Liu , Yong Zhou , Jiaqi Zhao , and Mingming Liu . 2020. Remote sensing image captioning via Variational Autoencoder and Reinforcement Learning. Knowledge-Based Systems ( 2020 ), 105920. Xiangqing Shen, Bing Liu, Yong Zhou, Jiaqi Zhao, and Mingming Liu. 2020. Remote sensing image captioning via Variational Autoencoder and Reinforcement Learning. Knowledge-Based Systems (2020), 105920."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.08.035"},{"key":"e_1_3_2_2_50_1","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics. Association for Computational Linguistics","author":"Song Kaiqiang","year":"2018","unstructured":"Kaiqiang Song , Lin Zhao , and Fei Liu . 2018 . Structure-Infused Copy Mechanisms for Abstractive Summarization . In Proceedings of the 27th International Conference on Computational Linguistics. Association for Computational Linguistics , Santa Fe, New Mexico, USA, 1717--1729. https:\/\/www.aclweb.org\/anthology\/C18--1146 Kaiqiang Song, Lin Zhao, and Fei Liu. 2018. Structure-Infused Copy Mechanisms for Abstractive Summarization. In Proceedings of the 27th International Conference on Computational Linguistics. Association for Computational Linguistics, Santa Fe, New Mexico, USA, 1717--1729. https:\/\/www.aclweb.org\/anthology\/C18--1146"},{"key":"e_1_3_2_2_51_1","volume-title":"Tel Aviv","author":"Tan Reuben","year":"2022","unstructured":"Reuben Tan , Bryan A. Plummer , Kate Saenko , JP Lewis , Avneesh Sud , and Thomas Leung . 2022 . NewsStories: Illustrating Articles with\u00a0Visual Summaries. In Computer Vision -- ECCV 2022: 17th European Conference , Tel Aviv , Israel, October 23-27, 2022, Proceedings, Part XXXVI (Tel Aviv, Israel). Springer-Verlag, Berlin, Heidelberg, 644--661. https:\/\/doi.org\/10.1007\/978-3-031- 20059-5_37 10.1007\/978-3-031-20059-5_37 Reuben Tan, Bryan A. Plummer, Kate Saenko, JP Lewis, Avneesh Sud, and Thomas Leung. 2022. NewsStories: Illustrating Articles with\u00a0Visual Summaries. In Computer Vision -- ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXVI (Tel Aviv, Israel). Springer-Verlag, Berlin, Heidelberg, 644--661. https:\/\/doi.org\/10.1007\/978-3-031-20059-5_37"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Joseph Tepperman David Traum and Shrikanth Narayanan. 2006. Yeah right: Sarcasm recognition for spoken dialogue systems. 1838--1841.  Joseph Tepperman David Traum and Shrikanth Narayanan. 2006. Yeah right: Sarcasm recognition for spoken dialogue systems. 1838--1841.","DOI":"10.21437\/Interspeech.2006-507"},{"key":"e_1_3_2_2_53_1","volume-title":"Garnett (Eds.)","volume":"29","author":"Tolstikhin Ilya O","year":"2016","unstructured":"Ilya O Tolstikhin , Bharath K. Sriperumbudur , and Bernhard Sch\u00f6lkopf . 2016 . Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels. In Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R . Garnett (Eds.) , Vol. 29 . Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/ 2016\/file\/5055cbf43fac3f7e2336b27310f0b9ef-Paper.pdf Ilya O Tolstikhin, Bharath K. Sriperumbudur, and Bernhard Sch\u00f6lkopf. 2016. Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels. In Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett (Eds.), Vol. 29. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2016\/file\/5055cbf43fac3f7e2336b27310f0b9ef-Paper.pdf"},{"key":"e_1_3_2_2_54_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4508"},{"key":"e_1_3_2_2_56_1","first-page":"19","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Wang Prince Zizhuang","year":"2019","unstructured":"Prince Zizhuang Wang and William Yang Wang . 2019 . Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling . In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 284--294. https:\/\/doi.org\/10. 18653\/v1\/N 19 - 1025 10.18653\/v1 Prince Zizhuang Wang and William Yang Wang. 2019. Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 284--294. https:\/\/doi.org\/10.18653\/v1\/N19-1025"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_38"},{"key":"e_1_3_2_2_58_1","volume-title":"Siu Cheung Hui, and Jie Fu.","author":"Zhang Aston","year":"2021","unstructured":"Aston Zhang , Yi Tay , Shuai Zhang , Alvin Chan , Anh Tuan Luu , Siu Cheung Hui, and Jie Fu. 2021 c. Beyond Fully-Connected Layers with Quaternions : Parameterization of Hypercomplex Multiplications with $1\/n$ Parameters . https:\/\/doi.org\/10.48550\/ARXIV.2102.08597 10.48550\/ARXIV.2102.08597 Aston Zhang, Yi Tay, Shuai Zhang, Alvin Chan, Anh Tuan Luu, Siu Cheung Hui, and Jie Fu. 2021c. Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1\/n$ Parameters. https:\/\/doi.org\/10.48550\/ARXIV.2102.08597"},{"key":"e_1_3_2_2_59_1","volume-title":"International Conference on Machine Learning. PMLR, 11328--11339","author":"Zhang Jingqing","year":"2020","unstructured":"Jingqing Zhang , Yao Zhao , Mohammad Saleh , and Peter Liu . 2020 . Pegasus: Pre-training with extracted gap-sentences for abstractive summarization . In International Conference on Machine Learning. PMLR, 11328--11339 . Jingqing Zhang, Yao Zhao, Mohammad Saleh, and Peter Liu. 2020. Pegasus: Pre-training with extracted gap-sentences for abstractive summarization. In International Conference on Machine Learning. PMLR, 11328--11339."},{"key":"e_1_3_2_2_60_1","unstructured":"Zhengkun Zhang Xiaojun Meng Yasheng Wang Xin Jiang Qun Liu and Zhenglu Yang. 2021a. UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation. https:\/\/doi.org\/10.48550\/ARXIV.2109.05812    10.48550\/ARXIV.2109.05812\nZhengkun Zhang Xiaojun Meng Yasheng Wang Xin Jiang Qun Liu and Zhenglu Yang. 2021a. UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation. https:\/\/doi.org\/10.48550\/ARXIV.2109.05812"},{"key":"e_1_3_2_2_61_1","volume-title":"ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization. https:\/\/doi.org\/10.48550\/ARXIV.2108.05123","author":"Zhang Zijian","year":"2021","unstructured":"Zijian Zhang , Chang Shu , Youxin Chen , Jing Xiao , Qian Zhang , and Lu Zheng . 2021 b. ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization. https:\/\/doi.org\/10.48550\/ARXIV.2108.05123 10.48550\/ARXIV.2108.05123 Zijian Zhang, Chang Shu, Youxin Chen, Jing Xiao, Qian Zhang, and Lu Zheng. 2021b. ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization. https:\/\/doi.org\/10.48550\/ARXIV.2108.05123"},{"key":"e_1_3_2_2_62_1","volume-title":"Sentence centrality revisited for unsupervised summarization. arXiv preprint arXiv:1906.03508","author":"Zheng Hao","year":"2019","unstructured":"Hao Zheng and Mirella Lapata . 2019. Sentence centrality revisited for unsupervised summarization. arXiv preprint arXiv:1906.03508 ( 2019 ). Hao Zheng and Mirella Lapata. 2019. Sentence centrality revisited for unsupervised summarization. arXiv preprint arXiv:1906.03508 (2019)."},{"key":"e_1_3_2_2_63_1","volume-title":"Towards Automatic Learning of Procedures From Web Instructional Videos. In AAAI Conference on Artificial Intelligence. 7590--7598","author":"Zhou Luowei","year":"2018","unstructured":"Luowei Zhou , Chenliang Xu , and Jason J Corso . 2018 . Towards Automatic Learning of Procedures From Web Instructional Videos. In AAAI Conference on Artificial Intelligence. 7590--7598 . https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/17344 Luowei Zhou, Chenliang Xu, and Jason J Corso. 2018. Towards Automatic Learning of Procedures From Web Instructional Videos. In AAAI Conference on Artificial Intelligence. 7590--7598. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/17344"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1448"}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599830","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:23Z","timestamp":1750182563000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":64,"alternative-id":["10.1145\/3580305.3599830","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599830","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}