{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:48:06Z","timestamp":1774352886102,"version":"3.50.1"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031702471","type":"print"},{"value":"9783031702488","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70248-8_17","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"219-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["M2DS: Multilingual Dataset for\u00a0Multi-document Summarisation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1580-0699","authenticated-orcid":false,"given":"Kushan","family":"Hewapathirana","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5361-4810","authenticated-orcid":false,"given":"Nisansa","family":"de Silva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4696-5210","authenticated-orcid":false,"given":"C.D.","family":"Athuraliya","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Abid, A.M.: Multi-document text summarization using deep belief network. Int. J. Adv. Sci. Res. Eng. (2022)","DOI":"10.31695\/IJASRE.2022.8.8.7"},{"issue":"37","key":"17_CR2","first-page":"68","volume":"1","author":"M Afsharizadeh","year":"2022","unstructured":"Afsharizadeh, M., Ebrahimpour-Komleh, H., et al.: A survey on multi-document summarization and domain-oriented approaches. J. Inf. Syst. Telecommun. 1(37), 68 (2022)","journal-title":"J. Inf. Syst. Telecommun."},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Angelidis, S., Lapata, M.: Summarizing opinions: Aspect extraction meets sentiment prediction and they are both weakly supervised. In: EMNLP, pp. 3675\u20133686 (2018)","DOI":"10.18653\/v1\/D18-1403"},{"key":"17_CR4","unstructured":"Beltagy, I., Peters, M.E., et\u00a0al.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"17_CR5","unstructured":"Chen, J., Cai, C., Jiang, X., Chen, K.: Comparative graph-based summarization of scientific papers guided by comparative citations. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 5978\u20135988 (2022)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"DeYoung, J., Beltagy, I., van Zuylen, M., Kuehl, B., Wang, L.L.: MS$$\\hat{2}$$: multi-document summarization of medical studies. In: EMNLP, pp. 7494\u20137513 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.594"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"DeYoung, J., Martinez, S.C., Marshall, I.J., Wallace, B.C.: Do multi-document summarization models synthesize? arXiv preprint arXiv:2301.13844 (2023)","DOI":"10.1162\/tacl_a_00687"},{"key":"17_CR8","unstructured":"Eberhard, D.M., G.F.S., Fennig, C.D.: Ethnologue: languages of the Americas and the pacific (2023)"},{"key":"17_CR9","unstructured":"Elhadad, M., Miranda-Jim\u00e9nez, S., Steinberger, J., Giannakopoulos, G.: Multi-document multilingual summarization corpus preparation, Part 2: Czech, Hebrew. In: Proceedings of the MultiLing 2013 Workshop on Multilingual Multi-document Summarization, pp. 13\u201319 (2013)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Fabbri, A.R., Li, I., She, T., Li, S., Radev, D.: Multi-news: a large-scale multi-document summarization dataset and abstractive hierarchical model. In: ACL, pp. 1074\u20131084 (2019)","DOI":"10.18653\/v1\/P19-1102"},{"key":"17_CR11","unstructured":"Ganesan, K., Zhai, C., Han, J.: Opinosis: a graph based approach to abstractive summarization of highly redundant opinions. In: Coling 2010, pp. 340\u2013348 (2010)"},{"key":"17_CR12","unstructured":"Giannakopoulos, G.: Multi-document multilingual summarization and evaluation tracks in ACL 2013 multiling workshop. In: Proceedings of the Multiling 2013 Workshop on Multilingual Multi-document Summarization, pp. 20\u201328 (2013)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Grusky, M., Naaman, M., Artzi, Y.: Newsroom: a dataset of 1.3 million summaries with diverse extractive strategies. In: ACL, pp. 708\u2013719 (2018)","DOI":"10.18653\/v1\/N18-1065"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Hasan, T., Bhattacharjee, et\u00a0al.: Xl-sum: large-scale multilingual abstractive summarization for 44 languages. In: ACL-IJCNLP 2021, pp. 4693\u20134703 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.413"},{"key":"17_CR15","unstructured":"Hermann, K.M., et al.: Teaching machines to read and comprehend. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Hewapathirana, K., De\u00a0Silva, N., Athuraliya, C.D.: Multi-document summarization: a comparative evaluation. In: 2023 IEEE 17th International Conference on Industrial and Information Systems (ICIIS), pp. 19\u201324. IEEE (2023)","DOI":"10.1109\/ICIIS58898.2023.10253581"},{"key":"17_CR17","unstructured":"Koupaee, M., Wang, W.Y.: Wikihow: a large scale text summarization dataset. arXiv preprint arXiv:1810.09305 (2018)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Ladhak, F., Durmus, E., Cardie, C., Mckeown, K.: Wikilingua: a new benchmark dataset for cross-lingual abstractive summarization. In: EMNLP 2020, pp. 4034\u20134048 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.360"},{"key":"17_CR19","unstructured":"Leon, S.: Rotten tomatoes movies and critic reviews dataset (2020). https:\/\/bit.ly\/RTdataset. Accessed 24 June 2023"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., et\u00a0al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL, pp. 7871\u20137880 (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"17_CR21","unstructured":"Li, L., For\u0103scu, C., El-Haj, M., Giannakopoulos, G.: Multi-document multilingual summarization corpus preparation, part 1: Arabic, English, Greek, Chinese, Romanian. In: Proceedings of the Multiling 2013 Workshop on Multilingual Multi-document Summarization, pp. 1\u201312 (2013)"},{"key":"17_CR22","unstructured":"Li, M., Qi, J., Lau, J.H.: Peersum: a peer review dataset for abstractive multi-document summarization. arXiv preprint arXiv:2203.01769 (2022)"},{"key":"17_CR23","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"17_CR24","unstructured":"Liu, P.J., Saleh, M., et\u00a0al.: Generating wikipedia by summarizing long sequences. arXiv preprint arXiv:1801.10198 (2018)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Liu, S., Cao, J., Yang, R., Wen, Z.: Generating a structured summary of numerous academic papers: dataset and method. arXiv preprint arXiv:2302.04580 (2023)","DOI":"10.24963\/ijcai.2022\/591"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lapata, M.: Text summarization with pretrained encoders. In: EMNLP-IJCNLP, pp. 3730\u20133740 (2019)","DOI":"10.18653\/v1\/D19-1387"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Lu, Y., Dong, Y., Charlin, L.: Multi-xscience: a large-scale dataset for extreme multi-document summarization of scientific articles. In: EMNLP, pp. 8068\u20138074 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.648"},{"key":"17_CR28","unstructured":"Ma, C., Zhang, W.E., et\u00a0al.: Multi-document summarization via deep learning techniques: a survey. ACM Comput. Surv. (2020)"},{"key":"17_CR29","unstructured":"Marina, L., Natalia, V.: Multilingual multi-document summarization with poly. In: Proceedings of the MultiLing 2013 Workshop on Multilingual Multi-document Summarization (2013)"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Moro, G., Ragazzi, L., Valgimigli, L., Freddi, D.: Discriminative marginalized probabilistic neural method for multi-document summarization of medical literature. In: ACL, pp. 180\u2013189 (2022)","DOI":"10.18653\/v1\/2022.acl-long.15"},{"key":"17_CR31","unstructured":"Napoles, C., Gormley, M.R., Van\u00a0Durme, B.: Annotated gigaword. In: Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction (AKBC-WEKEX), pp. 95\u2013100 (2012)"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Radev, D., Jing, H., Budzikowska, M.: Centroid-based summarization of multiple documents: sentence extraction, utility-based evaluation, and user studies. In: NAACL-ANLP 2000 Workshop: Automatic Summarization (2000)","DOI":"10.3115\/1567564.1567567"},{"key":"17_CR33","unstructured":"Raffel, C., Shazeer, N., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Salton, G.: A vector space model for information retrieval. J. ASIS 613\u2013620 (1975)","DOI":"10.1145\/361219.361220"},{"key":"17_CR35","unstructured":"Sandhaus, E.: The New York Times Annotated Corpus (2008). https:\/\/catalog.ldc.upenn.edu\/LDC2008T19"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Scialom, T.D., et\u00a0al.: Mlsum: the multilingual summarization corpus. In: EMNLP, pp. 8051\u20138067 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.647"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Sinha, A., Shen, Z., et\u00a0al.: An overview of Microsoft Academic Service (MAS) and applications. In: WWW, pp. 243\u2013246 (2015)","DOI":"10.1145\/2740908.2742839"},{"key":"17_CR38","unstructured":"Touvron, H., Martin, et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Verma, Y., Jangra, A., Verma, R., Saha, S.: Large scale multi-lingual multi-modal summarization dataset. In: ACL, pp. 3602\u20133614 (2023)","DOI":"10.18653\/v1\/2023.eacl-main.263"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Wang, D., Chen, J., Zhou, H., Qiu, X., Li, L.: Contrastive aligned joint learning for multilingual summarization. In: ACL-IJCNLP 2021, pp. 2739\u20132750 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.242"},{"key":"17_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, W., Beltagy, I., Carenini, G., Cohan, A.: Primera: pyramid-based masked sentence pre-training for multi-document summarization. In: ACL, pp. 5245\u20135263 (2022)","DOI":"10.18653\/v1\/2022.acl-long.360"},{"key":"17_CR42","unstructured":"Zhang, J., Zhao, Y., et\u00a0al.: Pegasus: pre-training with extracted gap-sentences for abstractive summarization. In: ICML, pp. 11328\u201311339. PMLR (2020)"}],"container-title":["Communications in Computer and Information Science","Advances in Computational Collective Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70248-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:12:42Z","timestamp":1725685962000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70248-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031702471","9783031702488"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70248-8_17","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Collective Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Leipzig","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccci2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccci.pwr.edu.pl\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}