{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T20:50:43Z","timestamp":1757451043445},"reference-count":31,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. &amp; Syst."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1587\/transinf.2022edp7083","type":"journal-article","created":{"date-parts":[[2022,12,31]],"date-time":"2022-12-31T22:17:22Z","timestamp":1672525042000},"page":"58-67","source":"Crossref","is-referenced-by-count":3,"title":["Auxiliary Loss for BERT-Based Paragraph Segmentation"],"prefix":"10.1587","volume":"E106.D","author":[{"given":"Binggang","family":"ZHUO","sequence":"first","affiliation":[{"name":"Tottori University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masaki","family":"MURATA","sequence":"additional","affiliation":[{"name":"Tottori University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"MA","sequence":"additional","affiliation":[{"name":"Ryukoku University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] R. Iikura, M. Okada, and N. Mori, \u201cImproving bert with focal loss for paragraph segmentation of novels,\u201d Int. Symp. Distributed Computing and Artificial Intelligence, pp.21-30, Springer, 2020. 10.1007\/978-3-030-53036-5_3","DOI":"10.1007\/978-3-030-53036-5_3"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] T.Y. Lin, P. Goyal, R. Girshick, K. He, and P. Doll\u00e1r, \u201cFocal loss for dense object detection,\u201d Proc. IEEE Int. Conf. Comput. Vis., pp.2980-2988, 2017. 10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"3","unstructured":"[3] J. Devlin, M.W. Chang, K. Lee, and K. Toutanova, \u201cBert: Pre-training of deep bidirectional transformers for language understanding,\u201d arXiv preprint arXiv:1810.04805, 2018. 10.48550\/arXiv.1810.04805"},{"key":"4","unstructured":"[4] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Advances in Neural Information Processing Systems, vol.30, pp.5998-6008, 2017."},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] K. Clark, U. Khandelwal, O. Levy, and C.D. Manning, \u201cWhat does bert look at? an analysis of bert&apos;s attention,\u201d arXiv preprint arXiv:1906.04341, 2019. 10.48550\/arXiv.1906.04341","DOI":"10.18653\/v1\/W19-4828"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] I. Pak and P.L. Teh, \u201cText segmentation techniques: a critical review,\u201d Innovative Computing, Optimization and Its Applications, pp.167-181, 2018. 10.1007\/978-3-319-66984-7_10","DOI":"10.1007\/978-3-319-66984-7_10"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] M. Naili, A.H. Chaibi, and H.H.B. Ghezala, \u201cComparative study of word embedding methods in topic segmentation,\u201d Procedia Computer Science, vol.112, pp.340-349, 2017. 10.1016\/j.procs.2017.08.009","DOI":"10.1016\/j.procs.2017.08.009"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] M.A.K. Halliday and R. Hasan, Cohesion in english, Routledge, 2014.","DOI":"10.4324\/9781315836010"},{"key":"9","unstructured":"[9] M.A. Hearst, \u201cTextTiling: Segmenting text into multi-paragraph subtopic passages,\u201d Computational linguistics, vol.23, no.1, pp.33-64, 1997."},{"key":"10","unstructured":"[10] F.Y.Y. Choi, \u201cAdvances in domain independent linear text segmentation,\u201d arXiv preprint cs\/0003083, 2000. 10.48550\/arXiv.cs\/0003083"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] M. Galley, K. McKeown, E. Fosler-Lussier, and H. Jing, \u201cDiscourse segmentation of multi-party conversation,\u201d Proc. 41st Annual Meeting of the Association for Computational Linguistics, vol.1, pp.562-569, July 2003. 10.3115\/1075096.1075167","DOI":"10.3115\/1075096.1075167"},{"key":"12","unstructured":"[12] O. Ferret, \u201cImproving text segmentation by combining endogenous and exogenous methods,\u201d Proc. Int. Conf. RANLP-2009, pp.88-93, 2009."},{"key":"13","unstructured":"[13] M. Riedl and C. Biemann, \u201cHow text segmentation algorithms gain from topic models,\u201d Proc. 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp.553-557, June 2012."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] S. Deerwester, S.T. Dumais, G.W. Furnas, T.K. Landauer, and R. Harshman, \u201cIndexing by latent semantic analysis,\u201d J. Am. Soc. Inf. Sci., vol.41, no.6, pp.391-407, 1990.","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"15","unstructured":"[15] T. Mikolov, K. Chen, G. Corrado, and J. Dean, \u201cEfficient estimation of word representations in vector space,\u201d arXiv preprint arXiv:1301.3781, 2013. 10.48550\/arXiv.1301.3781"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] J. Pennington, R. Socher, and C.D. Manning, \u201cGlove: Global vectors for word representation,\u201d Proc. 2014 Conf. empirical methods in natural language processing (EMNLP), pp.1532-1543, 2014.","DOI":"10.3115\/v1\/D14-1162"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] O. Koshorek, A. Cohen, N. Mor, M. Rotman, and J. Berant, \u201cText segmentation as a supervised learning task,\u201d arXiv preprint arXiv:1803.09337, 2018. 10.48550\/arXiv.1803.09337","DOI":"10.18653\/v1\/N18-2075"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] P. Badjatiya, L.J. Kurisinkel, M. Gupta, and V. Varma, \u201cAttention-based neural text segmentation,\u201d European Conf. Information Retrieval, pp.180-193, Springer, 2018. 10.1007\/978-3-319-76941-7_14","DOI":"10.1007\/978-3-319-76941-7_14"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] J. Li, A. Sun, and S.R. Joty, \u201cSegbot: A generic neural text segmentation model with pointer network,\u201d IJCAI, pp.4166-4172, 2018. 10.24963\/ijcai.2018\/579","DOI":"10.24963\/ijcai.2018\/579"},{"key":"20","unstructured":"[20] Y. Wang, S. Li, and J. Yang, \u201cToward fast and accurate neural discourse segmentation,\u201d arXiv preprint arXiv:1808.09147, 2018. 10.48550\/arXiv.1808.09147"},{"key":"21","unstructured":"[21] B. McCann, J. Bradbury, C. Xiong, and R. Socher, \u201cLearned in translation: Contextualized word vectors,\u201d Advances in Neural Information Processing Systems, vol.30, pp.6294-6305, 2017."},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] M. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer, \u201cDeep contextualized word representations. arxiv 2018,\u201d arXiv preprint arXiv:1802.05365, vol.12, 1802. 10.48550\/arXiv.1802.05365","DOI":"10.18653\/v1\/N18-1202"},{"key":"23","unstructured":"[23] A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever, \u201cImprov-ing language understanding by generative pre-training,\u201d OpenAI Technical Report, pp.1-12, 2018."},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] Y. Wang, Y. Hou, W. Che, and T. Liu, \u201cFrom static to dynamic word representations: a survey,\u201d Int. J. Mach. Learn. Cybern., vol.11, no.7, pp.1611-1630, 2020. 10.1007\/s13042-020-01069-8","DOI":"10.1007\/s13042-020-01069-8"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] M. Lukasik, B. Dadachev, G. Sim\u00f5es, and K. Papineni, \u201cText segmentation by cross segment attention,\u201d arXiv preprint arXiv:2004.14535, 2020. 10.48550\/arXiv.2004.14535","DOI":"10.18653\/v1\/2020.emnlp-main.380"},{"key":"26","unstructured":"[26] A. Solbiati, K. Heffernan, G. Damaskinos, S. Poddar, S. Modi, and J. Cali, \u201cUnsupervised topic segmentation of meetings with bert embeddings,\u201d arXiv preprint arXiv:2106.12978, 2021. 10.48550\/arXiv.2106.12978"},{"key":"27","unstructured":"[27] L. Xing, B. Hackinen, G. Carenini, and F. Trebbi, \u201cImproving context modeling in neural topic segmentation,\u201d arXiv preprint arXiv:2010.03138, 2020. 10.48550\/arXiv.2010.03138"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] I.A. Bolshakov and A. Gelbukh, \u201cText segmentation into paragraphs based on local text cohesion,\u201d Int. Conf. Text, Speech and Dialogue, pp.158-166, Springer, 2001. 10.1007\/3-540-44805-5_20","DOI":"10.1007\/3-540-44805-5_20"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] D. Genzel, \u201cA paragraph boundary detection system,\u201d Int. Conf. Intelligent Text Processing and Computational Linguistics, pp.816-826, Springer, 2005. 10.1007\/978-3-540-30586-6_92","DOI":"10.1007\/978-3-540-30586-6_92"},{"key":"30","doi-asserted-by":"publisher","unstructured":"[30] C. Sporleder and M. Lapata, \u201cBroad coverage paragraph segmentation across languages and domains,\u201d ACM Trans. Speech and Language Processing (TSLP), vol.3, no.2, pp.1-35, July 2006. 10.1145\/1149290.1151098","DOI":"10.1145\/1149290.1151098"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] K. Filippova and M. Strube, \u201cUsing linguistically motivated features for paragraph boundary identification,\u201d Proc. 2006 Conf. Empirical Methods in Natural Language Processing, pp.267-274, July 2006. 10.3115\/1610075.1610114","DOI":"10.3115\/1610075.1610114"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/1\/E106.D_2022EDP7083\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,19]],"date-time":"2023-03-19T14:58:32Z","timestamp":1679237912000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/1\/E106.D_2022EDP7083\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022edp7083","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,1]]},"article-number":"2022EDP7083"}}