{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T16:59:25Z","timestamp":1780851565844,"version":"3.54.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032281098","type":"print"},{"value":"9783032281104","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-28110-4_13","type":"book-chapter","created":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T16:31:06Z","timestamp":1780849866000},"page":"233-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["How Poor Data Quality Weakens the\u00a0Performance of\u00a0Question\u2014Answering Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3820-7870","authenticated-orcid":false,"given":"Camilla","family":"Sancricca","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Camilla","family":"Cesana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Gallo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arianna","family":"Gottardi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6062-5174","authenticated-orcid":false,"given":"Cinzia","family":"Cappiello","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"13_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-319-11749-2_8","volume-title":"Web Information Systems Engineering \u2013 WISE 2014","author":"S Albitar","year":"2014","unstructured":"Albitar, S., Fournier, S., Espinasse, B.: An effective TF\/IDF-based text-to-text semantic similarity measure for text classification. In: Benatallah, B., Bestavros, A., Manolopoulos, Y., Vakali, A., Zhang, Y. (eds.) WISE 2014. LNCS, vol. 8786, pp. 105\u2013114. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11749-2_8"},{"key":"13_CR2","unstructured":"Allam, A.M.N., Haggag, M.H.: The question answering systems: a survey. Int. J. Res. Rev. Inf. Sci. (IJRRIS) 2(3) (2012)"},{"issue":"3","key":"13_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","volume":"15","author":"Y Chang","year":"2024","unstructured":"Chang, Y., et al.: A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol. 15(3), 1\u201345 (2024)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"13_CR4","doi-asserted-by":"publisher","unstructured":"Fellbaum, C.: Wordnet. In: Poli, R., Healy, M., Kameas, A. (eds.) Theory and Applications of Ontology: Computer Applications, pp. 231\u2013243. Springer, Dordrecht (2010). https:\/\/doi.org\/10.1007\/978-90-481-8847-5_10","DOI":"10.1007\/978-90-481-8847-5_10"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Foroni, D., Lissandrini, M., Velegrakis, Y.: Estimating the extent of the effects of data quality through observations. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE), pp. 1913\u20131918. IEEE (2021)","DOI":"10.1109\/ICDE51399.2021.00176"},{"key":"13_CR6","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. arXiv preprint arXiv:2312.10997, 2(1) (2023)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Herzig, J., M\u00fcller, T., Krichene, S., Eisenschlos, J.M.: Open domain question answering over tables via dense retrieval. arXiv preprint arXiv:2103.12011 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.43"},{"key":"13_CR8","doi-asserted-by":"publisher","unstructured":"Jin, N., Siebert, J., Li, D., Chen, Q.: A survey on table question answering: recent advances. In: Sun, M., et al. (eds.) CCKS 2022. LNCS, vol. 1669, pp. 174\u2013186. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-981-19-7596-7_14","DOI":"10.1007\/978-981-19-7596-7_14"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Karra, R., Lasfar, A.: Impact of data quality on question answering system performances. Intell. Autom. Soft Comput. 35(1) (2023)","DOI":"10.32604\/iasc.2023.026695"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Lahitani, A.R., Permanasari, A.E., Setiawan, N.A.: Cosine similarity to determine similarity measure: study case in online essay assessment. In: 2016 4th International Conference on Cyber and IT Service Management, pp. 1\u20136. IEEE (2016)","DOI":"10.1109\/CITSM.2016.7577578"},{"key":"13_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2025.102549","volume":"132","author":"S Mohammed","year":"2025","unstructured":"Mohammed, S., et al.: The effects of data quality on machine learning performance on tabular data. Inf. Syst. 132, 102549 (2025)","journal-title":"Inf. Syst."},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Mukazhanov, N., Yerimbetova, A., Turdalyuly, M., Sakenov, B.: Named entities recognition in Kazakh text by spacy Ner models. In: 2024 9th International Conference on Computer Science and Engineering (UBMK), pp. 163\u2013168. IEEE (2024)","DOI":"10.1109\/UBMK63289.2024.10773475"},{"key":"13_CR13","unstructured":"PrimeQA: Clapnq dataset (2023). https:\/\/github.com\/primeqa\/clapnq. Accessed 10 Feb 2025"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Quinn, D., et al.: Accelerating retrieval-augmented generation. In: Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol. 1, pp. 15\u201332 (2025)","DOI":"10.1145\/3669940.3707264"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-Bert: sentence embeddings using Siamese Bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2019). https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"13_CR16","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/tacl_a_00729","volume":"13","author":"S Rosenthal","year":"2025","unstructured":"Rosenthal, S., Sil, A., Florian, R., Roukos, S.: CLAPnQ: Cohesive long-form answers from passages in natural questions for rag systems. Trans. Assoc. Comput. Linguistics 13, 53\u201372 (2025)","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Sancricca, C., Siracusa, G., Cappiello, C.: Enhancing data preparation: insights from a time series case study. J. Intell. Inf. Syst. 1\u201328 (2024)","DOI":"10.1007\/s10844-024-00867-8"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Sharma, R., Mahrishi, M., Morwal, S., Sharma, G.: Index point detection for text summarization using cosine similarity in educational videos. In: IOP Conference Series: Materials Science and Engineering, vol. 1131, p. 012001. IOP Publishing (2021)","DOI":"10.1088\/1757-899X\/1131\/1\/012001"},{"issue":"2","key":"13_CR19","first-page":"242","volume":"2","author":"B Sridevi","year":"2009","unstructured":"Sridevi, B., Nadarajan, R.: Fuzzy similarity measure for generalized fuzzy numbers. Int. J. Open Problems Compt. Math 2(2), 242\u2013253 (2009)","journal-title":"Int. J. Open Problems Compt. Math"},{"issue":"5","key":"13_CR20","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11280-024-01291-2","volume":"27","author":"L Wu","year":"2024","unstructured":"Wu, L., et al.: A survey on large language models for recommendation. World Wide Web 27(5), 60 (2024)","journal-title":"World Wide Web"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Robut: a systematic study of table QA robustness against human-annotated adversarial perturbations. arXiv preprint arXiv:2306.14321 (2023)","DOI":"10.18653\/v1\/2023.acl-long.334"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Zhou, W., Mesgar, M., Adel, H., Friedrich, A.: Freb-TQA: a fine-grained robustness evaluation benchmark for table question answering. arXiv preprint arXiv:2404.18585 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.137"}],"container-title":["Lecture Notes in Computer Science","Advanced Information Systems Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-28110-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T16:31:11Z","timestamp":1780849871000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-28110-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032281098","9783032281104"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-28110-4_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"8 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAiSE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Verona","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caise2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/caise26.polimi.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}