{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T23:46:25Z","timestamp":1782431185434,"version":"3.54.5"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030863364","type":"print"},{"value":"9783030863371","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\/978-3-030-86337-1_16","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:48:12Z","timestamp":1630702092000},"page":"236-250","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A More Effective Sentence-Wise Text Segmentation Approach Using BERT"],"prefix":"10.1007","author":[{"given":"Amit","family":"Maraj","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miguel Vargas","family":"Martin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masoud","family":"Makrehchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"16_CR1","unstructured":"Angelov, D.: Top2Vec: distributed representations of topics. arXiv:2008.09470 [cs, stat], August 2020)"},{"key":"16_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/978-3-319-76941-7_14","volume-title":"Advances in Information Retrieval","author":"P Badjatiya","year":"2018","unstructured":"Badjatiya, P., Kurisinkel, L.J., Gupta, M., Varma, V.: Attention-based neural text segmentation. In: Pasi, G., Piwowarski, B., Azzopardi, L., Hanbury, A. (eds.) ECIR 2018. LNCS, vol. 10772, pp. 180\u2013193. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-76941-7_14"},{"key":"16_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv:1409.0473 [cs, stat], May 2016"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Barrow, J., Jain, R., Morariu, V., Manjunatha, V., Oard, D., Resnik, P.: A joint model for document segmentation and segment labeling. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 313\u2013322. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.29, https:\/\/www.aclweb.org\/anthology\/2020.acl-main.29","DOI":"10.18653\/v1\/2020.acl-main.29"},{"issue":"1","key":"16_CR5","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1023\/A:1007506220214","volume":"34","author":"D Beeferman","year":"1999","unstructured":"Beeferman, D., Berger, A., Lafferty, J.: Statistical models for text segmentation. Mach. Learn. 34(1), 177\u2013210 (1999). https:\/\/doi.org\/10.1023\/A:1007506220214","journal-title":"Mach. Learn."},{"key":"16_CR6","unstructured":"Blei, D.M.: Latent Dirichlet Allocation, p. 30"},{"key":"16_CR7","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"16_CR8","unstructured":"Chaudhary, A.: A visual survey of data augmentation in NLP, May 2020. https:\/\/amitness.com\/2020\/05\/data-augmentation-for-nlp\/"},{"key":"16_CR9","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"key":"16_CR10","unstructured":"Choi, F.Y.Y.: Advances in domain independent linear text segmentation. arXiv:cs\/0003083, March 2000"},{"key":"16_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 [cs], May 2019"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Eisenstein, J., Barzilay, R.: Bayesian unsupervised topic segmentation. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp. 334\u2013343. Association for Computational Linguistics, Honolulu, October 2008. https:\/\/www.aclweb.org\/anthology\/D08-1035","DOI":"10.3115\/1613715.1613760"},{"key":"16_CR13","unstructured":"Hearst, M.A.: TextTiling: a quantitative approach to discourse segmentation. Technical report (1993)"},{"issue":"8","key":"16_CR14","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"16_CR15","doi-asserted-by":"publisher","unstructured":"Koshorek, O., Cohen, A., Mor, N., Rotman, M., Berant, J.: Text segmentation as a supervised learning task. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 469\u2013473. Association for Computational Linguistics, New Orleans, June 2018. https:\/\/doi.org\/10.18653\/v1\/N18-2075, https:\/\/www.aclweb.org\/anthology\/N18-2075","DOI":"10.18653\/v1\/N18-2075"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv:1508.04025 [cs], September 2015","DOI":"10.18653\/v1\/D15-1166"},{"key":"16_CR17","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/6754.001.0001","volume-title":"The Theory and Practice of Discourse Parsing and Summarization","author":"D Marcu","year":"2000","unstructured":"Marcu, D.: The Theory and Practice of Discourse Parsing and Summarization. MIT Press, Cambridge (2000).Google-Books-ID: VyjED9VOn5MC"},{"key":"16_CR18","unstructured":"McCann, B., Bradbury, J., Xiong, C., Socher, R.: Learned in translation: contextualized word vectors. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 6294\u20136305. Curran Associates, Inc. (2017). http:\/\/papers.nips.cc\/paper\/7209-learned-in-translation-contextualized-word-vectors.pdf"},{"key":"16_CR19","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv:1301.3781 [cs], September 2013"},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Misra, H., Yvon, F., Jose, J.M., Cappe, O.: Text segmentation via topic modeling: an analytical study. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management. CIKM 2009, pp. 1553\u20131556. Association for Computing Machinery, New York, November 2009. https:\/\/doi.org\/10.1145\/1645953.1646170","DOI":"10.1145\/1645953.1646170"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Mueller, J., Thyagarajan, A.: Siamese recurrent architectures for learning sentence similarity. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, no. 1, March 2016. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/10350, number: 1","DOI":"10.1609\/aaai.v30i1.10350"},{"key":"16_CR22","doi-asserted-by":"publisher","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543. Association for Computational Linguistics, Doha, October 2014. https:\/\/doi.org\/10.3115\/v1\/D14-1162, https:\/\/www.aclweb.org\/anthology\/D14-1162","DOI":"10.3115\/v1\/D14-1162"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. arXiv:1802.05365 [cs], March 2018","DOI":"10.18653\/v1\/N18-1202"},{"issue":"1","key":"16_CR24","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1162\/089120102317341756","volume":"28","author":"L Pevzner","year":"2002","unstructured":"Pevzner, L., Hearst, M.A.: A critique and improvement of an evaluation metric for text segmentation. Comput. Linguist. 28(1), 19\u201336 (2002)","journal-title":"Comput. Linguist."},{"key":"16_CR25","doi-asserted-by":"publisher","unstructured":"Purver, M., K\u00f6rding, K.P., Griffiths, T.L., Tenenbaum, J.B.: Unsupervised topic modelling for multi-party spoken discourse. In: Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pp. 17\u201324. Association for Computational Linguistics, Sydney, July 2006. https:\/\/doi.org\/10.3115\/1220175.1220178, https:\/\/www.aclweb.org\/anthology\/P06-1003","DOI":"10.3115\/1220175.1220178"},{"key":"16_CR26","doi-asserted-by":"publisher","unstructured":"Qiu, S., et al.: EasyAug: an automatic textual data augmentation platform for classification tasks. In: Companion Proceedings of the Web Conference 2020. WWW 2020, pp. 249\u2013252. Association for Computing Machinery, New York, April 2020. https:\/\/doi.org\/10.1145\/3366424.3383552","DOI":"10.1145\/3366424.3383552"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text, June 2016. https:\/\/arxiv.org\/abs\/1606.05250v3","DOI":"10.18653\/v1\/D16-1264"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv:1908.10084 [cs], August 2019","DOI":"10.18653\/v1\/D19-1410"},{"key":"16_CR29","unstructured":"Riedl, M., Biemann, C.: TopicTiling: a text segmentation algorithm based on LDA. In: Proceedings of ACL 2012 Student Research Workshop, pp. 37\u201342. Association for Computational Linguistics, Jeju Island, July 2012. https:\/\/www.aclweb.org\/anthology\/W12-3307"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Mcclelland, J.L.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1. Foundations (1986)","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"16_CR31","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv:1910.01108 [cs], February 2020"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv:1508.07909 [cs], June 2016","DOI":"10.18653\/v1\/P16-1162"},{"key":"16_CR33","unstructured":"Shoa, S.: Contextual Topic Identification: Identifying meaningful topics for sparse Steam reviews, March 2020. Publication Title: Medium"},{"key":"16_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 5998\u20136008. Curran Associates, Inc. (2017). http:\/\/papers.nips.cc\/paper\/7181-attention-is-all-you-need.pdf"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding, April 2018. https:\/\/arxiv.org\/abs\/1804.07461v3","DOI":"10.18653\/v1\/W18-5446"},{"key":"16_CR36","doi-asserted-by":"publisher","unstructured":"Wang, W.Y., Yang, D.: That\u2019s so annoying!!!: a lexical and frame-semantic embedding based data augmentation approach to automatic categorization of annoying behaviors using #petpeeve tweets. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 2557\u20132563. Association for Computational Linguistics, Lisbon, September 2015. https:\/\/doi.org\/10.18653\/v1\/D15-1306, https:\/\/www.aclweb.org\/anthology\/D15-1306","DOI":"10.18653\/v1\/D15-1306"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Wei, J., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks, January 2019. https:\/\/arxiv.org\/abs\/1901.11196v2","DOI":"10.18653\/v1\/D19-1670"},{"key":"16_CR38","unstructured":"Williams, A., Nangia, N., Bowman, S.R.: A broad-coverage challenge corpus for sentence understanding through inference, April 2017. https:\/\/arxiv.org\/abs\/1704.05426v4"},{"key":"16_CR39","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. arXiv:1609.08144 [cs], October 2016"},{"key":"16_CR40","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation for consistency training. arXiv:1904.12848 [cs, stat], November 2020"},{"key":"16_CR41","unstructured":"Yang, H.: BERT meets Chinese word segmentation, September 2019. https:\/\/arxiv.org\/abs\/1909.09292v1"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Lee Giles, C.: Learning to extract semantic structure from documents using multimodal fully convolutional neural networks, pp. 5315\u20135324 (2017). https:\/\/openaccess.thecvf.com\/content_cvpr_2017\/html\/Yang_Learning_to_Extract_CVPR_2017_paper.html","DOI":"10.1109\/CVPR.2017.462"},{"key":"16_CR43","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv:1710.09412 [cs, stat], April 2018"},{"key":"16_CR44","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. arXiv:1509.01626 [cs], April 2016"}],"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\/978-3-030-86337-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:05:30Z","timestamp":1756850730000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86337-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863364","9783030863371"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86337-1_16","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)"}}]}}