{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T06:44:04Z","timestamp":1781246644645,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,13]]},"DOI":"10.1145\/3711542.3711576","type":"proceedings-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T04:46:56Z","timestamp":1744606016000},"page":"272-278","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["From Unstructured Documents to Annotated Information: An Optimized Pipeline to Process Industrial Requirements"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6138-5720","authenticated-orcid":false,"given":"Nocente","family":"Arianna","sequence":"first","affiliation":[{"name":"Department of Information Engineering, University of Pisa, Pisa, Italy and Alstom Ferroviaria Spa, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0622-4564","authenticated-orcid":false,"given":"Risi","family":"Riccardo","sequence":"additional","affiliation":[{"name":"Marketing Division, Columbia Business School, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5578-344X","authenticated-orcid":false,"given":"Pannocchia","family":"Gabriele","sequence":"additional","affiliation":[{"name":"Department of Civil and Industrial Engineering, University of Pisa, Pisa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3373-1240","authenticated-orcid":false,"given":"Rossetti","family":"Giulio","sequence":"additional","affiliation":[{"name":"Institute of Science and Technologies, Italian National Research Council (CNR), Pisa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,13]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Muhammad Abbas Alessio Ferrari Anas Shatnawi Eduard Enoiu Mehrdad Saadatmand and Daniel Sundmark. 2023. On the relationship between similar requirements and similar software: A case study in the railway domain. Requirements Engineering 28 1 (2023) 23\u201347.","DOI":"10.1007\/s00766-021-00370-4"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-29786-1_8"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Manal Binkhonain and Liping Zhao. 2019. A review of machine learning algorithms for identification and classification of non-functional requirements. Expert Systems with Applications: X 1 (2019) 100001.","DOI":"10.1016\/j.eswax.2019.100001"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Leo Breiman. 2001. Random forests. Machine learning 45 (2001) 5\u201332.","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Agustin Casamayor Daniela Godoy and Marcelo Campo. 2010. Identification of non-functional requirements in textual specifications: A semi-supervised learning approach. Information and Software Technology 52 4 (2010) 436\u2013445.","DOI":"10.1016\/j.infsof.2009.10.010"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Jair Cervantes Farid Garcia-Lamont Lisbeth Rodr\u00edguez-Mazahua and Asdrubal Lopez. 2020. A comprehensive survey on support vector machine classification: Applications challenges and trends. Neurocomputing 408 (2020) 189\u2013215.","DOI":"10.1016\/j.neucom.2019.10.118"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Jane Cleland-Huang Raffaella Settimi Xuchang Zou and Peter Solc. 2007. Automated classification of non-functional requirements. Requirements engineering 12 (2007) 103\u2013120.","DOI":"10.1007\/s00766-007-0045-1"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-35510-4_6"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2017.29"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Parisa Ghazi and Martin Glinz. 2017. Challenges of working with artifacts in requirements engineering and software engineering. Requirements Engineering 22 (2017) 359\u2013385.","DOI":"10.1007\/s00766-017-0272-z"},{"key":"e_1_3_3_2_12_2","unstructured":"Ming Jiang Yuerong Hu Glen Worthey Ryan\u00a0C Dubnicek Ted Underwood and J\u00a0Stephen Downie. 2021. Impact of OCR quality on BERT embeddings in the domain classification of book excerpts. Proceedings http:\/\/ceur-ws. org ISSN 1613 (2021) 0073."},{"key":"e_1_3_3_2_13_2","first-page":"488","volume-title":"Advances in Artificial Intelligence","author":"Kibriya Ashraf\u00a0M","year":"2005","unstructured":"Ashraf\u00a0M Kibriya, Eibe Frank, Bernhard Pfahringer, and Geoffrey Holmes. 2005. Multinomial naive bayes for text categorization revisited. In Advances in Artificial Intelligence. Springer, 488\u2013499."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2017.82"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10397400"},{"key":"e_1_3_3_2_16_2","first-page":"3","volume-title":"Advanced Information Systems Engineering","author":"Moser Thomas","year":"2011","unstructured":"Thomas Moser, Dietmar Winkler, Matthias Heindl, and Stefan Biffl. 2011. Requirements management with semantic technology: An empirical study on automated requirements categorization and conflict analysis. In Advanced Information Systems Engineering. Springer, 3\u201317."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Chao-Ying\u00a0Joanne Peng Kuk\u00a0Lida Lee and Gary\u00a0M Ingersoll. 2002. An introduction to logistic regression analysis and reporting. The journal of educational research 96 1 (2002) 3\u201314.","DOI":"10.1080\/00220670209598786"},{"key":"e_1_3_3_2_18_2","first-page":"65","volume-title":"Document Analysis Systems","author":"Shafait Faisal","year":"2010","unstructured":"Faisal Shafait and Ray Smith. 2010. Table detection in heterogeneous documents.. In Document Analysis Systems (2010-07-07), David\u00a0S. Doermann, Venu Govindaraju, Daniel\u00a0P. Lopresti, and Premkumar Natarajan (Eds.). ACM, 65\u201372."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/NAturaLiSE.2013.6611715"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/1577802.1577804"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Riad Sonbol Ghaida Rebdawi and Nada Ghneim. 2022. The use of nlp-based text representation techniques to support requirement engineering tasks: A systematic mapping review. Ieee Access 10 (2022) 62811\u201362830.","DOI":"10.1109\/ACCESS.2022.3182372"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Archana Tikayat\u00a0Ray Bjorn\u00a0F Cole Olivia\u00a0J Pinon\u00a0Fischer Ryan\u00a0T White and Dimitri\u00a0N Mavris. 2023. aerobert-classifier: Classification of aerospace requirements using bert. Aerospace 10 3 (2023) 279.","DOI":"10.3390\/aerospace10030279"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/1577802.1577809"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Liping Zhao Waad Alhoshan Alessio Ferrari Keletso\u00a0J Letsholo Muideen\u00a0A Ajagbe Erol-Valeriu Chioasca and Riza\u00a0T Batista-Navarro. 2021. Natural language processing for requirements engineering: A systematic mapping study. ACM Computing Surveys (CSUR) 54 3 (2021) 1\u201341.","DOI":"10.1145\/3444689"}],"event":{"name":"NLPIR 2024: 2024 8th International Conference on Natural Language Processing and Information Retrieval","location":"Okayama Japan","acronym":"NLPIR 2024"},"container-title":["Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711542.3711576","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711542.3711576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:29Z","timestamp":1750295909000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711542.3711576"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":23,"alternative-id":["10.1145\/3711542.3711576","10.1145\/3711542"],"URL":"https:\/\/doi.org\/10.1145\/3711542.3711576","relation":{},"subject":[],"published":{"date-parts":[[2024,12,13]]},"assertion":[{"value":"2025-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}