{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:11:10Z","timestamp":1750219870093,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":42,"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\/3543507.3583405","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:25Z","timestamp":1682551825000},"page":"1703-1713","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7144-4520","authenticated-orcid":false,"given":"Dhaval","family":"Taunk","sequence":"first","affiliation":[{"name":"International Institute of Information Technology, Hyderabad, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-4586","authenticated-orcid":false,"given":"Shivprasad","family":"Sagare","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology, Hyderabad, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6034-7987","authenticated-orcid":false,"given":"Anupam","family":"Patil","sequence":"additional","affiliation":[{"name":"SCTR's Pune Institute of Computer Technology, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5647-1790","authenticated-orcid":false,"given":"Shivansh","family":"Subramanian","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology, Hyderabad, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2843-3110","authenticated-orcid":false,"given":"Manish","family":"Gupta","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology, Hyderabad, India and Microsoft India, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1923-1725","authenticated-orcid":false,"given":"Vasudeva","family":"Varma","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology, Hyderabad, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages. In The World Wide Web Conference. 171\u2013175","author":"Abhishek Tushar","year":"2022","unstructured":"Tushar Abhishek, Shivprasad Sagare, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta, and Vasudeva Varma. 2022. XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages. In The World Wide Web Conference. 171\u2013175."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference. 6645\u20136650","author":"Antognini Diego","year":"2020","unstructured":"Diego Antognini and Boi Faltings. 2020. GameWikiSum: a Novel Large Multi-Document Summarization Dataset. In Proceedings of the 12th Language Resources and Evaluation Conference. 6645\u20136650."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. Association for Computational Linguistics","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. Association for Computational Linguistics, Ann Arbor, Michigan, 65\u201372. https:\/\/aclanthology.org\/W05-0909"},{"key":"e_1_3_2_1_4_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150(2020).","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_5_1","unstructured":"Sahil\u00a0Manoj Bhatt Sahaj Agarwal Omkar Gurjar Manish Gupta and Manish Shrivastava. 2023. TourismNLG: A Multi-lingual Generative Benchmark for the Tourism Domain. In ECIR. To appear."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Z Chi L Dong S Ma S Huang X-L Mao H Huang and F Wei. 2021. MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs. arxiv:2104.08692\u00a0[cs.CL]","DOI":"10.18653\/v1\/2021.emnlp-main.125"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Z Chi L Dong F Wei W Wang X-L Mao and H Huang. 2020. Cross-lingual natural language generation via pre-training. In AAAI Vol.\u00a034. 7570\u20137577.","DOI":"10.1609\/aaai.v34i05.6256"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Alexis Conneau Kartikay Khandelwal Naman Goyal Vishrav Chaudhary Guillaume Wenzek Francisco Guzm\u00e1n Edouard Grave Myle Ott Luke Zettlemoyer and Veselin Stoyanov. 2019. Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116(2019).","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_9_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018).","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. arXiv preprint arXiv:1810.04805(2018)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1483"},{"key":"e_1_3_2_1_11_1","unstructured":"Yue Dong Andrei Mircea and Jackie\u00a0CK Cheung. 2020. Discourse-aware unsupervised summarization of long scientific documents. arXiv preprint arXiv:2005.00513(2020)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"C Gardent A Shimorina S Narayan and L Perez-Beltrachini. 2017. The WebNLG challenge: Generating text from RDF data. In INLG. 124\u2013133.","DOI":"10.18653\/v1\/W17-3518"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.120"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4638"},{"key":"e_1_3_2_1_15_1","unstructured":"Tahmid Hasan Abhik Bhattacharjee Wasi\u00a0Uddin Ahmad Yuan-Fang Li Yong-Bin Kang and Rifat Shahriyar. 2021. CrossSum: Beyond English-Centric Cross-Lingual Abstractive Text Summarization for 1500+ Language Pairs. arXiv preprint arXiv:2112.08804(2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Tahmid Hasan Abhik Bhattacharjee Md\u00a0Saiful Islam Kazi Samin Yuan-Fang Li Yong-Bin Kang M\u00a0Sohel Rahman and Rifat Shahriyar. 2021. XL-sum: Large-scale multilingual abstractive summarization for 44 languages. arXiv preprint arXiv:2106.13822(2021).","DOI":"10.18653\/v1\/2021.findings-acl.413"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00362"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290614"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.445"},{"key":"e_1_3_2_1_20_1","volume-title":"Reformer: The Efficient Transformer. In International Conference on Learning Representations.","author":"Kitaev Nikita","year":"2019","unstructured":"Nikita Kitaev, Lukasz Kaiser, and Anselm Levskaya. 2019. Reformer: The Efficient Transformer. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Faisal Ladhak Esin Durmus Claire Cardie and Kathleen McKeown. 2020. WikiLingua: A new benchmark dataset for cross-lingual abstractive summarization. arXiv preprint arXiv:2010.03093(2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.360"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"R Lebret D Grangier and M Auli. 2016. Neural Text Generation from Structured Data with Application to the Biography Domain. In EMNLP. 1203\u20131213.","DOI":"10.18653\/v1\/D16-1128"},{"key":"e_1_3_2_1_23_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL. 7871\u20137880.","author":"Lewis M","year":"2020","unstructured":"M Lewis, Y Liu, N Goyal, M Ghazvininejad, A Mohamed, O Levy, V Stoyanov, and L Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL. 7871\u20137880."},{"key":"e_1_3_2_1_24_1","volume-title":"Xglue: A new benchmark dataset for cross-lingual pre-training, understanding and generation. arXiv:2004.01401","author":"Liang Y","year":"2020","unstructured":"Y Liang, N Duan, Y Gong, N Wu, F Guo, W Qi, M Gong, L Shou, D Jiang, G Cao, 2020. Xglue: A new benchmark dataset for cross-lingual pre-training, understanding and generation. arXiv:2004.01401 (2020)."},{"key":"e_1_3_2_1_25_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_26_1","unstructured":"Peter\u00a0J Liu Mohammad Saleh Etienne Pot Ben Goodrich Ryan Sepassi Lukasz Kaiser and Noam Shazeer. 2018. Generating wikipedia by summarizing long sequences. arXiv preprint arXiv:1801.10198(2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"H Mei M Bansal and M\u00a0R Walter. 2016. What to talk about and how? Selective Gen. using LSTMs with Coarse-to-Fine Alignment. In NAACL-HLT. 720\u2013730.","DOI":"10.18653\/v1\/N16-1086"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3469403"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"P Nema S Shetty P Jain A Laha K Sankaranarayanan and M\u00a0M Khapra. 2018. Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization. In NAACL-HLT. 1539\u20131550.","DOI":"10.18653\/v1\/N18-1139"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5411"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4770"},{"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.J","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter\u00a0J Liu, 2020. Exploring the limits of transfer learning with a unified text-to-text transformer.J. Mach. Learn. Res. 21, 140 (2020), 1\u201367.","journal-title":"Mach. Learn. Res."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"L\u00a0F\u00a0R Ribeiro M Schmitt H Sch\u00fctze and I Gurevych. 2021. Investigating Pretrained Language Models for Graph-to-Text Generation. arxiv:2007.08426\u00a0[cs.CL]","DOI":"10.18653\/v1\/2021.nlp4convai-1.20"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Shivprasad Sagare Tushar Abhishek Bhavyajeet Singh Anubhav Sharma Manish Gupta and Vasudeva Varma. 2022. XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages. arXiv preprint arXiv:2209.11252(2022).","DOI":"10.18653\/v1\/2023.inlg-main.2"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.647"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"H Shahidi M Li and J Lin. 2020. Two Birds One Stone: A Simple Unified Model for Text Generation from Structured and Unstructured Data. In ACL. 3864\u20133870.","DOI":"10.18653\/v1\/2020.acl-main.355"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Pavel Tikhonov and Valentin Malykh. 2022. WikiMulti: a Corpus for Cross-Lingual Summarization. arXiv preprint arXiv:2204.11104(2022).","DOI":"10.1007\/978-3-031-23372-2_6"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.websem.2018.07.002"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.45"},{"key":"e_1_3_2_1_42_1","volume-title":"NCLS: Neural Cross-Lingual Summarization. In EMNLP-IJCNLP. 3054\u20133064.","author":"Zhu J","year":"2019","unstructured":"J Zhu, Q Wang, Y Wang, Y Zhou, J Zhang, S Wang, and C Zong. 2019. NCLS: Neural Cross-Lingual Summarization. In EMNLP-IJCNLP. 3054\u20133064."}],"event":{"name":"WWW '23: The ACM Web Conference 2023","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Austin TX USA","acronym":"WWW '23"},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583405","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:52Z","timestamp":1750178872000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583405"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":42,"alternative-id":["10.1145\/3543507.3583405","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583405","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"}}]}}