{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:29:49Z","timestamp":1781609389164,"version":"3.54.5"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030863302","type":"print"},{"value":"9783030863319","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86331-9_6","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"84-98","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["CoMSum and SIBERT: A Dataset and Neural Model for Query-Based Multi-document Summarization"],"prefix":"10.1007","author":[{"given":"Sayali","family":"Kulkarni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheide","family":"Chammas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Sha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eugene","family":"Ie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"6_CR1","unstructured":"Bajaj, P., et al.: MS MARCO: a human generated machine reading comprehension dataset (2018)"},{"key":"6_CR2","unstructured":"Baumel, T., Eyal, M., Elhadad, M.: Query focused abstractive summarization: incorporating query relevance, multi-document coverage, and summary length constraints into seq2seq models. CoRR abs\/1801.07704 (2018). http:\/\/arxiv.org\/abs\/1801.07704"},{"key":"6_CR3","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer (2020)"},{"key":"6_CR4","unstructured":"Cer, D., et al.: Universal sentence encoder. CoRR abs\/1803.11175 (2018). http:\/\/arxiv.org\/abs\/1803.11175"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Dang, H.T.: Duc 2005: evaluation of question-focused summarization systems. In: Proceedings of the Workshop on Task-Focused Summarization and Question Answering, SumQA 2006, pp. 48\u201355. Association for Computational Linguistics, USA (2006)","DOI":"10.3115\/1654679.1654689"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Daum\u00e9 III, H., Marcu, D.: Bayesian query-focused summarization. In: Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pp. 305\u2013312. Association for Computational Linguistics, Sydney (July 2006). https:\/\/www.aclweb.org\/anthology\/P06-1039","DOI":"10.3115\/1220175.1220214"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Deng, Y., et al.: Joint learning of answer selection and answer summary generation in community question answering. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i05.6266"},{"key":"6_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2019)"},{"key":"6_CR9","unstructured":"Diego Antognini, B.F.: Gamewikisum: a novel large multi-document summarization dataset. LREC (2020). https:\/\/arxiv.org\/abs\/2002.06851"},{"key":"6_CR10","unstructured":"Dunn, M., Sagun, L., Higgins, M., Guney, V.U., Cirik, V., Cho, K.: SearchQA: a new q&a dataset augmented with context from a search engine (2017)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Egonmwan, E., Castelli, V., Sultan, M.A.: Cross-task knowledge transfer for query-based text summarization. In: Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pp. 72\u201377. Association for Computational Linguistics, Hong Kong (November 2019). https:\/\/www.aclweb.org\/anthology\/D19-5810","DOI":"10.18653\/v1\/D19-5810"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Fabbri, A.R., Li, I., She, T., Li, S., Radev, D.R.: Multi-news: a large-scale multi-document summarization dataset and abstractive hierarchical model. ACL (2019)","DOI":"10.18653\/v1\/P19-1102"},{"key":"6_CR13","unstructured":"Ghalandari, D.G., Hokamp, C., Pham, N.T., Glover, J., Ifrim, G.: A large-scale multi-document summarization dataset from the Wikipedia current events portal. ACL (2020). https:\/\/arxiv.org\/abs\/2005.10070"},{"key":"6_CR14","unstructured":"Hasselqvist, J., Helmertz, N., K\u00e5geb\u00e4ck, M.: Query-based abstractive summarization using neural networks. CoRR abs\/1712.06100 (2017). http:\/\/arxiv.org\/abs\/1712.06100"},{"key":"6_CR15","unstructured":"Hermann, K.M., et al.: Teaching machines to read and comprehend. In: Advances in Neural Information Processing Systems, pp. 1693\u20131701 (2015)"},{"key":"6_CR16","unstructured":"Hermann, K.M., et al.: Teaching machines to read and comprehend. CoRR abs\/1506.03340 (2015). http:\/\/arxiv.org\/abs\/1506.03340"},{"key":"6_CR17","first-page":"174","volume":"12036","author":"T Ishigaki","year":"2020","unstructured":"Ishigaki, T., Huang, H.H., Takamura, H., Chen, H.H., Okumura, M.: Neural query-biased abstractive summarization using copying mechanism. Adv. Inf. Retr. 12036, 174\u2013181 (2020)","journal-title":"Adv. Inf. Retr."},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Joshi, M., Choi, E., Weld, D., Zettlemoyer, L.: TriviaQA: a large scale distantly supervised challenge dataset for reading comprehension, pp. 1601\u20131611. Association for Computational Linguistics, Vancouver (July 2017). https:\/\/www.aclweb.org\/anthology\/P17-1147","DOI":"10.18653\/v1\/P17-1147"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Kazemi, A., Prez-Rosas, V., Mihalcea, R.: Biased TextRank: unsupervised graph-based content extraction (2020)","DOI":"10.18653\/v1\/2020.coling-main.144"},{"key":"6_CR20","unstructured":"Koupaee, M., Wang, W.Y.: Wikihow: a large scale text summarization dataset. CoRR abs\/1810.09305 (2018). http:\/\/arxiv.org\/abs\/1810.09305"},{"key":"6_CR21","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1162\/tacl_a_00276","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., et al.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 453\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Li, W., Xiao, X., Liu, J., Wu, H., Wang, H., Du, J.: Leveraging graph to improve abstractive multi-document summarization. ACL (2020). https:\/\/arxiv.org\/abs\/2005.10043","DOI":"10.18653\/v1\/2020.acl-main.555"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Litvak, M., Vanetik, N.: Query-based summarization using MDL principle. In: Proceedings of the MultiLing 2017 Workshop on Summarization and Summary Evaluation Across Source Types and Genres, pp. 22\u201331. Association for Computational Linguistics, Valencia (April 2017). https:\/\/www.aclweb.org\/anthology\/W17-1004","DOI":"10.18653\/v1\/W17-1004"},{"key":"6_CR24","unstructured":"Liu, P.J., et al.: Generating Wikipedia by summarizing long sequences. CoRR abs\/1801.10198 (2018). http:\/\/arxiv.org\/abs\/1801.10198"},{"key":"6_CR25","unstructured":"Liu, T., Moore, A.W., Gray, A.G., Yang, K.: An investigation of practical approximate nearest neighbor algorithms. In: NIPS (2004)"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lapata, M.: Hierarchical transformers for multi-document summarization. ACL (2019). arXiv:1905.13164","DOI":"10.18653\/v1\/P19-1500"},{"key":"6_CR27","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. In: NeurIPS (2020). https:\/\/arxiv.org\/abs\/2007.14062"},{"key":"6_CR28","unstructured":"Mihalcea, R., Tarau, P.: TextRank: bringing order into text. In: Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pp. 404\u2013411. Association for Computational Linguistics, Barcelona (July 2004). https:\/\/www.aclweb.org\/anthology\/W04-3252"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Nallapati, R., Zhou, B., Gulcehre, C., Xiang, B., et al.: Abstractive text summarization using sequence-to-sequence RNNs and beyond. Computational Natural Language Learning (2016)","DOI":"10.18653\/v1\/K16-1028"},{"key":"6_CR30","doi-asserted-by":"publisher","unstructured":"Nema, P., Khapra, M.M., Laha, A., Ravindran, B.: Diversity driven attention model for query-based abstractive summarization. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30\u2013August 4, vol. 1: Long Papers, pp. 1063\u20131072. Association for Computational Linguistics (2017). https:\/\/doi.org\/10.18653\/v1\/P17-1098","DOI":"10.18653\/v1\/P17-1098"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Otterbacher, J., Erkan, G., Radev, D.R.: Biased LexRank: passage retrieval using random walks with question-based priors. Inf. Process. Manag. 45(1), 42\u201354 (2009). http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0306457308000666","DOI":"10.1016\/j.ipm.2008.06.004"},{"key":"6_CR32","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv e-prints (2019)"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Rossiello, G., Basile, P., Semeraro, G.: Centroid-based text summarization through compositionality of word embeddings. ACL (2017). https:\/\/www.aclweb.org\/anthology\/W17-1003","DOI":"10.18653\/v1\/W17-1003"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Rush, A.M., Chopra, S., Weston, J.: A neural attention model for abstractive sentence summarization. In: EMNLP (2015)","DOI":"10.18653\/v1\/D15-1044"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Schilder, F., Kondadadi, R.: Fastsum: fast and accurate query-based multi-document summarization. In: Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers, HLT-Short 2008, pp. 205\u2013208. Association for Computational Linguistics, USA (2008)","DOI":"10.3115\/1557690.1557748"},{"key":"6_CR36","unstructured":"See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks. CoRR abs\/1704.04368 (2017). http:\/\/arxiv.org\/abs\/1704.04368"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Su, D., Xu, Y., Yu, T., Siddique, F.B., Barezi, E.J., Fung, P.: Caire-covid: a question answering and query-focused multi-document summarization system for covid-19 scholarly information management. In: EMNLP2020 NLP-COVID Workshop (2020). https:\/\/arxiv.org\/abs\/2005.03975","DOI":"10.18653\/v1\/2020.nlpcovid19-2.14"},{"key":"6_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-015-0564-6","volume":"16","author":"G Tsatsaronis","year":"2015","unstructured":"Tsatsaronis, G., Balikas, G., Malakasiotis, P., et al.: An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition. BMC Bioinform. 16, 1\u201328 (2015). https:\/\/doi.org\/10.1186\/s12859-015-0564-6","journal-title":"BMC Bioinform."},{"key":"6_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need (2017)"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Self-supervised learning for contextualized extractive summarization. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2221\u20132227. Association for Computational Linguistics, Florence (July 2019). https:\/\/www.aclweb.org\/anthology\/P19-1214","DOI":"10.18653\/v1\/P19-1214"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Wang, L., Yao, J., Tao, Y., Zhong, L., Liu, W., Du, Q.: A reinforced topic-aware convolutional sequence-to-sequence model for abstractive text summarization. CoRR abs\/1805.03616 (2018). http:\/\/arxiv.org\/abs\/1805.03616","DOI":"10.24963\/ijcai.2018\/619"},{"key":"6_CR42","unstructured":"Wang, L., Raghavan, H., Castelli, V., Florian, R., Cardie, C.: A sentence compression based framework to query-focused multi-document summarization. CoRR abs\/1606.07548 (2016). http:\/\/arxiv.org\/abs\/1606.07548"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: HotpotQA: a dataset for diverse, explainable multi-hop question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2369\u20132380. Association for Computational Linguistics, Brussels (October\u2013November 2018). https:\/\/www.aclweb.org\/anthology\/D18-1259","DOI":"10.18653\/v1\/D18-1259"},{"key":"6_CR44","unstructured":"Zhang, J., Zhao, Y., Saleh, M., Liu, P.J.: Pegasus: pre-training with extracted gap-sentences for abstractive summarization. ArXiv abs\/1912.08777 (2019)"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, F., Zhou, M.: HIBERT: document level pre-training of hierarchical bidirectional transformers for document summarization. CoRR abs\/1905.06566 (2019). http:\/\/arxiv.org\/abs\/1905.06566","DOI":"10.18653\/v1\/P19-1499"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86331-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:05:17Z","timestamp":1756937117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86331-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863302","9783030863319"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86331-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","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":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"340","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"182","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.9","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Additionally, 13 competition reports are included.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}