{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:46:32Z","timestamp":1740181592426,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T00:00:00Z","timestamp":1694649600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T00:00:00Z","timestamp":1694649600000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-023-02148-7","type":"journal-article","created":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T15:02:06Z","timestamp":1694703726000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Extraction of Conversation Flows from Human Dialogues: Understanding Their Impact to Refine NLP Models"],"prefix":"10.1007","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6904-7873","authenticated-orcid":false,"given":"Matheus Ferraroni","family":"Sanches","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jader Martins Camboim","family":"de S\u00e1","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael Roque","family":"de Souza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allan Mariano","family":"de Souza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julio Cesar","family":"Dos Reis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leandro Aparecido","family":"Villas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,14]]},"reference":[{"issue":"10","key":"2148_CR1","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1007\/s11431-020-1647-3","volume":"63","author":"X Qiu","year":"2020","unstructured":"Qiu X, Sun T, Xu Y, Shao Y, Dai N, Huang X. Pre-trained models for natural language processing: a survey. Sci China Technol Sci. 2020;63(10):1872\u201397. https:\/\/doi.org\/10.1007\/s11431-020-1647-3.","journal-title":"Sci China Technol Sci"},{"issue":"1","key":"2148_CR2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1080\/07421222.1993.11517988","volume":"10","author":"A Bansal","year":"1993","unstructured":"Bansal A, Kauffman RJ, Weitz RR. Comparing the modeling performance of regression and neural networks as data quality varies: a business value approach. J Manag Inf Syst. 1993;10(1):11\u201332. https:\/\/doi.org\/10.1080\/07421222.1993.11517988.","journal-title":"J Manag Inf Syst"},{"key":"2148_CR3","doi-asserted-by":"publisher","DOI":"10.1145\/3457607","author":"N Mehrabi","year":"2021","unstructured":"Mehrabi N, Morstatter F, Saxena N, Lerman K, Galstyan A. A survey on bias and fairness in machine learning. ACM Comput Surv. 2021. https:\/\/doi.org\/10.1145\/3457607.","journal-title":"ACM Comput Surv."},{"key":"2148_CR4","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K, Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 2018."},{"key":"2148_CR5","doi-asserted-by":"publisher","unstructured":"Yang Z, Dai Z, Yang Y, Carbonell J, Salakhutdinov R, Le QV, XLNet: Generalized Autoregressive Pretraining for Language Understanding. arXiv 2019. https:\/\/doi.org\/10.48550\/ARXIV.1906.08237. https:\/\/arxiv.org\/abs\/1906.08237.","DOI":"10.48550\/ARXIV.1906.08237"},{"key":"2148_CR6","doi-asserted-by":"publisher","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V, RoBERTa: a robustly optimized BERT pretraining approach. arXiv 2019. https:\/\/doi.org\/10.48550\/ARXIV.1907.11692. https:\/\/arxiv.org\/abs\/1907.11692.","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"2148_CR7","doi-asserted-by":"publisher","unstructured":"Zhu Y, Kiros R, Zemel R, Salakhutdinov R, Urtasun R, Torralba A, Fidler S, Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books. arXiv 2015. https:\/\/doi.org\/10.48550\/ARXIV.1506.06724. https:\/\/arxiv.org\/abs\/1506.06724","DOI":"10.48550\/ARXIV.1506.06724"},{"key":"2148_CR8","doi-asserted-by":"crossref","unstructured":"Souza F, Nogueira R, Lotufo R, BERTimbau: pretrained BERT models for Brazilian Portuguese. In: 9th Brazilian Conference on Intelligent Systems, BRACIS, Rio Grande do Sul, Brazil, October 20-23 (to Appear) 2020.","DOI":"10.1007\/978-3-030-61377-8_28"},{"key":"2148_CR9","doi-asserted-by":"publisher","unstructured":"Parker, Robert, Graff, David, Kong, Junbo, Chen, Ke, Maeda, Kazuaki, English Gigaword Fifth Edition. Linguistic Data Consortium (2011). https:\/\/doi.org\/10.35111\/WK4F-QT80. https:\/\/catalog.ldc.upenn.edu\/LDC2011T07","DOI":"10.35111\/WK4F-QT80"},{"key":"2148_CR10","doi-asserted-by":"publisher","unstructured":"Wang A, Singh A, Michael J, Hill F, Levy O, Bowman S, GLUE: A multi-task benchmark and analysis platform for natural language understanding. In: Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks For NLP, pp. 353\u2013355. Association for Computational Linguistics, Brussels, Belgium 2018. https:\/\/doi.org\/10.18653\/v1\/W18-5446. https:\/\/aclanthology.org\/W18-5446","DOI":"10.18653\/v1\/W18-5446"},{"key":"2148_CR11","doi-asserted-by":"crossref","unstructured":"Lai G, Xie Q, Liu H, Yang Y, Hovy E, Race: Large-scale reading comprehension dataset from examinations. arXiv preprint arXiv:1704.04683 2017.","DOI":"10.18653\/v1\/D17-1082"},{"key":"2148_CR12","doi-asserted-by":"publisher","unstructured":"Rajpurkar P, Zhang J, Lopyrev K, Liang P. SQuAD: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016;2383\u20132392. Association for Computational Linguistics, Austin, Texas. https:\/\/doi.org\/10.18653\/v1\/D16-1264. https:\/\/aclanthology.org\/D16-1264","DOI":"10.18653\/v1\/D16-1264"},{"key":"2148_CR13","unstructured":"Nagel S. News Dataset. commoncrawl 2016. https:\/\/commoncrawl.org\/2016\/10\/news-dataset-available\/"},{"key":"2148_CR14","unstructured":"Gokaslan A, Cohen V. OpenWebText Corpus. http:\/\/Skylion007.github.io\/OpenWebTextCorpus 2019"},{"key":"2148_CR15","doi-asserted-by":"publisher","unstructured":"Trinh TH, Le QV. A Simple Method for Commonsense Reasoning. arXiv 2018. https:\/\/doi.org\/10.48550\/ARXIV.1806.02847. https:\/\/arxiv.org\/abs\/1806.02847","DOI":"10.48550\/ARXIV.1806.02847"},{"key":"2148_CR16","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan TJ, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D. Language models are few-shot learners. ArXiv abs\/2005.14165 2020."},{"key":"2148_CR17","doi-asserted-by":"publisher","unstructured":"Sanches, M, C. de S\u00e1 J, M. de Souza, A, Silva, D, R. de Souza, R, Reis J, Villas, L, MCCD: Generating Human Natural Language Conversational Datasets. In: Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS,, 2022;247\u2013255. SciTePress, Virtual Conference . https:\/\/doi.org\/10.5220\/0011077400003179. INSTICC","DOI":"10.5220\/0011077400003179"},{"key":"2148_CR18","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language models are unsupervised multitask learners. In: OpenAI 2019."},{"key":"2148_CR19","doi-asserted-by":"crossref","unstructured":"Peters ME, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L. Deep contextualized word representations. In: Proc. of NAACL 2018.","DOI":"10.18653\/v1\/N18-1202"},{"key":"2148_CR20","doi-asserted-by":"publisher","unstructured":"Traum DR. In: Wooldridge, M., Rao, A. (eds.) Speech Acts for Dialogue Agents, 1999;169\u2013201. Springer, Dordrecht. https:\/\/doi.org\/10.1007\/978-94-015-9204-8_8.","DOI":"10.1007\/978-94-015-9204-8_8"},{"key":"2148_CR21","doi-asserted-by":"publisher","unstructured":"Wolf MJ, Miller KW, Grodzinsky FS. Why we should have seen that coming: Comments on microsoft\u2019s tay \u201cexperiment,\u201d and wider implications. ORBIT J 1(2), 1\u201312 (2017). https:\/\/doi.org\/10.29297\/orbit.v1i2.49","DOI":"10.29297\/orbit.v1i2.49"},{"key":"2148_CR22","unstructured":"Wagner\u00a0Filho JA, Wilkens R, Idiart M, Villavicencio A, The brWaC corpus: A new open resource for Brazilian Portuguese. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA), Miyazaki, Japan 2018. https:\/\/aclanthology.org\/L18-1686"},{"key":"2148_CR23","unstructured":"Smith JR, Saint-Amand H, Plamada M, Koehn P, Callison-Burch C, Lopez A, Dirt cheap web-scale parallel text from the Common Crawl. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2013;1374\u20131383. Association for Computational Linguistics, Sofia, Bulgaria. https:\/\/aclanthology.org\/P13-1135"},{"key":"2148_CR24","doi-asserted-by":"crossref","unstructured":"Lowe R, Pow N, Serban I, Pineau J, The ubuntu dialogue corpus: a large dataset for research in unstructured multi-turn dialogue systems. 2015. arXiv preprint arXiv:1506.08909","DOI":"10.18653\/v1\/W15-4640"},{"key":"2148_CR25","doi-asserted-by":"publisher","unstructured":"Budzianowski P, Wen T-H, Tseng B-H, Casanueva I, Ultes S, Ramadan O, Ga\u0161ic M, Multiwoz - a large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue modelling. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing 2018. https:\/\/doi.org\/10.18653\/v1\/d18-1547","DOI":"10.18653\/v1\/d18-1547"},{"issue":"1","key":"2148_CR26","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1145\/357417.357420","volume":"2","author":"JF Kelley","year":"1984","unstructured":"Kelley JF. An iterative design methodology for user-friendly natural language office information applications. ACM Trans Inf Syst. 1984;2(1):26\u201341. https:\/\/doi.org\/10.1145\/357417.357420.","journal-title":"ACM Trans Inf Syst"},{"issue":"3","key":"2148_CR27","doi-asserted-by":"publisher","first-page":"4","DOI":"10.5087\/dad.2016.301","volume":"7","author":"JD Williams","year":"2016","unstructured":"Williams JD, Raux A, Henderson M. The dialog state tracking challenge series: a review. Dialogue Discourse. 2016;7(3):4\u201333.","journal-title":"Dialogue Discourse"},{"key":"2148_CR28","unstructured":"Li Y, Su H, Shen X, Li W, Cao Z, Niu S. DailyDialog: A manually labelled multi-turn dialogue dataset. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2017;986\u2013995. Asian Federation of Natural Language Processing, Taipei, Taiwan . https:\/\/aclanthology.org\/I17-1099"},{"key":"2148_CR29","doi-asserted-by":"publisher","unstructured":"Byrne B, Krishnamoorthi K, Sankar C, Neelakantan A, Goodrich B, Duckworth D Yavuz S, Dubey A, Kim K-Y, Cedilnik A. Taskmaster-1: Toward a realistic and diverse dialog dataset. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) 2019. https:\/\/doi.org\/10.18653\/v1\/d19-1459","DOI":"10.18653\/v1\/d19-1459"},{"issue":"12","key":"2148_CR30","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1145\/3458723","volume":"64","author":"T Gebru","year":"2021","unstructured":"Gebru T, Morgenstern J, Vecchione B, Vaughan JW, Wallach H, Iii HD, Crawford K. Datasheets for datasets. Commun ACM. 2021;64(12):86\u201392.","journal-title":"Commun ACM"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-02148-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-023-02148-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-02148-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T15:23:16Z","timestamp":1694704996000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-023-02148-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,14]]},"references-count":30,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["2148"],"URL":"https:\/\/doi.org\/10.1007\/s42979-023-02148-7","relation":{},"ISSN":["2661-8907"],"issn-type":[{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2023,9,14]]},"assertion":[{"value":"21 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"706"}}