{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T07:15:10Z","timestamp":1760426110897,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T00:00:00Z","timestamp":1652659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,16]]},"DOI":"10.1145\/3522664.3528604","type":"proceedings-article","created":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T16:30:14Z","timestamp":1666024214000},"page":"145-156","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Data is about detail"],"prefix":"10.1145","author":[{"given":"Anmol","family":"Singhal","sequence":"first","affiliation":[{"name":"TCS Research, New Delhi, India"}]},{"given":"Preethu Rose","family":"Anish","sequence":"additional","affiliation":[{"name":"TCS Research, Pune, MH, India"}]},{"given":"Pratik","family":"Sonar","sequence":"additional","affiliation":[{"name":"TCS Research, Pune, MH, India"}]},{"given":"Smita S","family":"Ghaisas","sequence":"additional","affiliation":[{"name":"TCS Research, Pune, MH, India"}]}],"member":"320","published-online":{"date-parts":[[2022,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2018966.2018979"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICBDAA.2017.8284116"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00042"},{"key":"e_1_3_2_1_4_1","first-page":"14","volume-title":"Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics:Technical Papers. Dublin City University and Association for Computational Linguistics","author":"Angrosh Mandya","year":"2014","unstructured":"Mandya Angrosh, Tadashi Nomoto, and Advaith Siddharthan. 2014. Lexico-syntactic text simplification and compression with typed dependencies. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics:Technical Papers. Dublin City University and Association for Computational Linguistics, Dublin, Ireland, 1996--2006. https:\/\/aclanthology.org\/C14-1188"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/REW53955.2021.00021"},{"key":"e_1_3_2_1_6_1","volume-title":"Software Engineering Challenges of Deep Learning. CoRR abs\/1810.12034","author":"Arpteg Anders","year":"2018","unstructured":"Anders Arpteg, Bj\u00f6rn Brinne, Luka Crnkovic-Friis, and Jan Bosch. 2018. Software Engineering Challenges of Deep Learning. CoRR abs\/1810.12034 (2018). arXiv:1810.12034 http:\/\/arxiv.org\/abs\/1810.12034"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/REW.2019.00051"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswax.2019.100001"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Su Blodgett Solon Barocas Hal III and Hanna Wallach. 2020. Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP. 5454--5476. 10.18653\/v1\/2020.acl-main.485","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"e_1_3_2_1_10_1","volume-title":"Engineering AI Systems: A Research Agenda. CoRR abs\/2001.07522","author":"Bosch Jan","year":"2020","unstructured":"Jan Bosch, Ivica Crnkovic, and Helena Holmstr\u00f6m Olsson. 2020. Engineering AI Systems: A Research Agenda. CoRR abs\/2001.07522 (2020). arXiv:2001.07522 https:\/\/arxiv.org\/abs\/2001.07522"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the International Workshop on Software-intensive Business: Start-ups, Ecosystems and Platforms (SiBW 2018), Espoo, Finland, December 3, 2018 (CEUR Workshop Proceedings","volume":"192","author":"Bosch Jan","year":"2018","unstructured":"Jan Bosch, Helena Holmstr\u00f6m Olsson, and Ivica Crnkovic. 2018. It takes three to tango: Requirement, outcome\/data, and AI driven development. In Proceedings of the International Workshop on Software-intensive Business: Start-ups, Ecosystems and Platforms (SiBW 2018), Espoo, Finland, December 3, 2018 (CEUR Workshop Proceedings, Vol. 2305). CEUR-WS.org, 177--192. http:\/\/ceur-ws.org\/Vol-2305\/paper14.pdf"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01307-2_43"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/AIRE51212.2020.00016"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.7748\/nr.13.4.84.s4"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Ranit Chatterjee Abdul Ahmed and Preethu Rose. 2020. Identification and Classification of Architecturally Significant Functional Requirements. 10.1109\/AIRE51212.2020.00008","DOI":"10.1109\/AIRE51212.2020.00008"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.04.003"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics","author":"Coster William","year":"2011","unstructured":"William Coster and David Kauchak. 2011. Simple English Wikipedia: A New Text Simplification Task. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Portland, Oregon, USA, 665--669. https:\/\/aclanthology.org\/P11-2117"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-1308"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5401"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2016.01.001"},{"key":"e_1_3_2_1_22_1","unstructured":"Steven Y. Feng Varun Gangal Jason Wei Sarath Chandar Soroush Vosoughi Teruko Mitamura and Eduard Hovy. 2021. A Survey of Data Augmentation Approaches for NLP. arXiv:2105.03075 [cs.CL]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11073184"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3470817"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/sam.10061"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9101670"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3106280"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3138\/cjpe.30.1.108"},{"key":"e_1_3_2_1_30_1","unstructured":"Matthew Honnibal and Ines Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings convolutional neural networks and incremental parsing. (2017). To appear."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2019.00050"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Timothy Hospedales Antreas Antoniou Paul Micaelli and Amos Storkey. 2020. Meta-Learning in Neural Networks: A Survey. arXiv:2004.05439 [cs.LG]","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","unstructured":"Jeremy Howard and Sebastian Ruder. 2018. Universal Language Model Fine-tuning for Text Classification. 10.48550\/ARXIV.1801.06146","DOI":"10.48550\/ARXIV.1801.06146"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Jeremy Howard and Sebastian Ruder. 2018. Universal Language Model Fine-tuning for Text Classification. arXiv:1801.06146 [cs.CL]","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_3_2_1_35_1","unstructured":"N. King and C. Horrocks. 2010. Interviews in Qualitative Research. SAGE Publications. https:\/\/books.google.co.in\/books?id=iOsnITKC48gC"},{"key":"e_1_3_2_1_36_1","volume-title":"NEURIPS 2021 Workshop for Data Centric AI.","author":"Lavitas Liliya","year":"2021","unstructured":"Liliya Lavitas, Olivia Redfield, Allen Lee, Daniel Fletcher, Matthias Eck, and Sunil Janardhanan. 2021. Annotation Quality Framework-Accuracy, Credibility, and Consistency. In NEURIPS 2021 Workshop for Data Centric AI."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.45"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8536"},{"key":"e_1_3_2_1_39_1","volume-title":"Anna Maria Vollmer, and Stefan Wagner","author":"Mart\u00ednez-Fern\u00e1ndez Silverio","year":"2021","unstructured":"Silverio Mart\u00ednez-Fern\u00e1ndez, Justus Bogner, Xavier Franch, Marc Oriol, Julien Siebert, Adam Trendowicz, Anna Maria Vollmer, and Stefan Wagner. 2021. Software Engineering for AI-Based Systems: A Survey. CoRR abs\/2105.01984 (2021). arXiv:2105.01984 https:\/\/arxiv.org\/abs\/2105.01984"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACHI.2008.34"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/int.20432"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","unstructured":"Fredrik Olsson and Magnus Sahlgren. 2020. Data Readiness for Natural Language Processing. 10.48550\/ARXIV.2009.02043","DOI":"10.48550\/ARXIV.2009.02043"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5121\/ijsea.2021.12303"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3240727"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157497"},{"key":"e_1_3_2_1_46_1","volume-title":"op den Akker","author":"Reidsma Dennis","year":"2008","unstructured":"Dennis Reidsma and Hendrikus J.A. op den Akker. 2008. Exploiting \"Subjective\" Annotations. In Coling 2008: Proceedings of the workshop on Human Judgements in Computational Linguistics, R. Artstein, G. Boleda, F. Keller, and S. Schulte im Walde (Eds.). Coling 2008 Organizing Committee, 8--16. https:\/\/research.utwente.nl\/en\/publications\/exploiting-subjective-annotations"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-008-9102-8"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3229867"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.3390\/en12091696"},{"key":"e_1_3_2_1_51_1","unstructured":"Han-Sub Shin and Hyuk-Yoon Kwon. 2020. Weakly Supervised Learning for Judging the Credibility of Movie Reviews. arXiv:2010.05025 [cs.IR]"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58793-2_2"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955903"},{"key":"e_1_3_2_1_54_1","volume-title":"Requirements Engineering for Machine Learning: Perspectives from Data Scientists. CoRR abs\/1908.04674","author":"Vogelsang Andreas","year":"2019","unstructured":"Andreas Vogelsang and Markus Borg. 2019. Requirements Engineering for Machine Learning: Perspectives from Data Scientists. CoRR abs\/1908.04674 (2019). arXiv:1908.04674 http:\/\/arxiv.org\/abs\/1908.04674"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474840"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1904.05046"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1162\/0891201041850885"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.3115\/1034678.1034721"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","unstructured":"Karina Wiechork and Andrea Char\u00e3o. 2021. Automated Data Extraction from PDF Documents: Application to Large Sets of Educational Tests. 10.5220\/0010524503590366","DOI":"10.5220\/0010524503590366"},{"key":"e_1_3_2_1_60_1","unstructured":"R. J. Wieringa and M. Jackson. 2003. Design Methods for Reactive Systems: Yourdon Statemate and the UML. Elsevier Science. https:\/\/books.google.st\/books?id=XmU89hDzZqIC"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24396-7_32"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/2145432.2145480"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1108\/02635570210414668"},{"key":"e_1_3_2_1_64_1","volume-title":"Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010","author":"Zhu Zhemin","year":"2010","unstructured":"Zhemin Zhu, Delphine Bernhard, and Iryna Gurevych. 2010. A Monolingual Tree-based Translation Model for Sentence Simplification. In Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010). Coling 2010 Organizing Committee, Beijing, China, 1353--1361. https:\/\/aclanthology.org\/C10-1152"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73105-4_40"}],"event":{"name":"CAIN '22: 1st Conference on AI Engineering - Software Engineering for AI","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE TCSC IEEE Technical Committee on Scalable Computing"],"location":"Pittsburgh Pennsylvania","acronym":"CAIN '22"},"container-title":["Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3522664.3528604","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3522664.3528604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:34Z","timestamp":1750183774000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3522664.3528604"}},"subtitle":["an empirical investigation for software systems with NLP at core"],"short-title":[],"issued":{"date-parts":[[2022,5,16]]},"references-count":65,"alternative-id":["10.1145\/3522664.3528604","10.1145\/3522664"],"URL":"https:\/\/doi.org\/10.1145\/3522664.3528604","relation":{},"subject":[],"published":{"date-parts":[[2022,5,16]]},"assertion":[{"value":"2022-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}