{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T19:10:07Z","timestamp":1758913807040,"version":"3.44.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061355","type":"print"},{"value":"9783032061362","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"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\/978-3-032-06136-2_18","type":"book-chapter","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T18:37:58Z","timestamp":1758911878000},"page":"185-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Enrichment in\u00a0SQL Workflows Through Targeted LLM Invocation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2785-946X","authenticated-orcid":false,"given":"Yannis","family":"Foufoulas","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0426-337X","authenticated-orcid":false,"given":"Eleni","family":"Zacharia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9791-587X","authenticated-orcid":false,"given":"Harry","family":"Dimitropoulos","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3477-3082","authenticated-orcid":false,"given":"Natalia","family":"Manola","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1705-8247","authenticated-orcid":false,"given":"Yannis","family":"Ioannidis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"issue":"1","key":"18_CR1","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MCSE.2019.2943847","volume":"22","author":"F Kr\u00fcger","year":"2020","unstructured":"Kr\u00fcger, F., Schindler, D.: A literature review on methods for the extraction of usage statements of software and data. Comput. Sci. Eng. 22(1), 26\u201338 (2020)","journal-title":"Comput. Sci. Eng."},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Colavizza, G., et al.: The citation advantage of linking publications to research data. PLoS One 15(4) (2020)","DOI":"10.1371\/journal.pone.0230416"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Federer, L.M., et al.: Data sharing in PLOS ONE: An analysis of Data Availability Statements. PLoS One, vol. 13, no. 5, 2018","DOI":"10.1371\/journal.pone.0194768"},{"key":"18_CR4","unstructured":"Brown, T. B., et. al.: Language Models are Few-Shot Learners. arXiv preprint arXiv:2005.14165v4 (2020)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Rostam, Z.R.K., et.al.: Achieving peak performance for large language models: a systematic review. IEEE Access, 96017\u201396050 (2024)","DOI":"10.1109\/ACCESS.2024.3424945"},{"issue":"3","key":"18_CR6","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s00799-023-00358-1","volume":"25","author":"Y Foufoulas","year":"2024","unstructured":"Foufoulas, Y., et al.: Detexa: declarative extensible text exploration and analysis through sql. Int. J. Digit. Libr. 25(3), 457\u2013469 (2024)","journal-title":"Int. J. Digit. Libr."},{"key":"18_CR7","doi-asserted-by":"publisher","unstructured":"Foufoulas, Y., et al.: Detexa: Declarative extensible text exploration and analysis. In: International Conference on Theory and Practice of Digital Libraries, pp. 107-119. Springer International Publishing (2022). https:\/\/doi.org\/10.1007\/978-3-031-16802-4_9","DOI":"10.1007\/978-3-031-16802-4_9"},{"issue":"10","key":"18_CR8","first-page":"2270","volume":"15","author":"Y Foufoulas","year":"2022","unstructured":"Foufoulas, Y., et al.: Yesql: you extend sql with rich and highly performant user-defined functions in relational databases. PVLDB 15(10), 2270\u20132283 (2022)","journal-title":"PVLDB"},{"key":"18_CR9","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.15223404","author":"V McCutcheon","year":"2025","unstructured":"McCutcheon, V., et al.: Ukrn data accessibility statement pilot classification discussion document. Zenodo (2025). https:\/\/doi.org\/10.5281\/zenodo.15223404","journal-title":"Zenodo"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Harris, David J., et al. Can cognitive training capitalise on near transfer effects? Limited evidence of transfer following online inhibition training in a randomised-controlled trial. PLoS One 18(11) (2023)","DOI":"10.1371\/journal.pone.0293657"},{"key":"18_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.biortech.2022.128485","volume":"369","author":"ZH Ouderji","year":"2023","unstructured":"Ouderji, Z.H., et al.: Integration of anaerobic digestion with heat pump: machine learning-based technical and environmental assessment. Biores. Technol. 369, 128485 (2023)","journal-title":"Biores. Technol."},{"key":"18_CR12","doi-asserted-by":"publisher","unstructured":"Karvelas, A., et al.: Investigating learning join order optimization strategies for rule-based data engines. Inform. Syst. Front. (2024). https:\/\/doi.org\/10.1007\/s10796-024-10555-1","DOI":"10.1007\/s10796-024-10555-1"},{"issue":"12","key":"18_CR13","first-page":"3874","volume":"16","author":"Y Foufoulas","year":"2023","unstructured":"Foufoulas, Y., Simitsis, A.: Efficient execution of user-defined functions in sql queries. PVLDB 16(12), 3874\u20133877 (2023)","journal-title":"PVLDB"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Foufoulas, Y., Simitsis, A. User-defined functions in modern data engines. In: IEEE ICDE, pp. 3593-3598 (2023)","DOI":"10.1109\/ICDE55515.2023.00276"},{"key":"18_CR15","unstructured":"Foufoulas, Y., Palaiologou, T., Simitsis, A.: UDFBench:ATool for Benchmarking UDF Queries on SQL Engines, SIGMOD (2025)"},{"issue":"12","key":"18_CR16","first-page":"3730","volume":"15","author":"Y Foufoulas","year":"2022","unstructured":"Foufoulas, Y., Simitsis, A., Ioannidis, Y.: Yesql: rich user-defined functions without the overhead. PVLDB 15(12), 3730\u20133733 (2022)","journal-title":"PVLDB"},{"key":"18_CR17","unstructured":"Kl\u00e4be, S., et al.: Accelerating python udfs in vectorized query execution. In: CIDR (2022)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Spiegelberg, L., et al.: Tuplex: data science in python at native code speed. In: Proceedings of the 2021 International Conference on Management of Data, pp. 1718-1731 (2021)","DOI":"10.1145\/3448016.3457244"},{"key":"18_CR19","doi-asserted-by":"publisher","unstructured":"Sichert, M., Neumann, T.: User-defined operators: efficiently integrating custom algorithms into modern databases. PVLDB 15(5) (2022). https:\/\/doi.org\/10.14778\/3510397.3510408","DOI":"10.14778\/3510397.3510408"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Chasialis, K., et al.: QFusor: a UDF optimizer plugin for SQL databases. In: IEEE ICDE, pp. 5457-5460 (2024). https:\/\/doi.org\/10.1109\/ICDE60146.2024.00427","DOI":"10.1109\/ICDE60146.2024.00427"},{"key":"18_CR21","unstructured":"Blacher, M., et al.: Machine learning, linear algebra, and more: Is SQL all you need?. In: CIDR (2022)"},{"key":"18_CR22","doi-asserted-by":"publisher","unstructured":"Hellerstein, J.M., et al.: The MADlib analytics library. PVLDB 5(12), 1700-1711 (2012).https:\/\/doi.org\/10.14778\/2367502.2367510","DOI":"10.14778\/2367502.2367510"},{"key":"18_CR23","doi-asserted-by":"publisher","unstructured":"Giannakopoulos, T., et al.: Discovering and visualizing interdisciplinary content classes in scientific publications. D-Lib Mag. 20(11\/12) (2014). https:\/\/doi.org\/10.1045\/november14-giannakopoulos","DOI":"10.1045\/november14-giannakopoulos"},{"key":"18_CR24","doi-asserted-by":"publisher","unstructured":"Giannakopoulos, T., et.al.: Visual-based classification of figures from scientific literature. In: Proceedings of the 24th International Conference on World Wide Web, pp 1059-1060, (2015). https:\/\/doi.org\/10.1145\/2740908.2742024","DOI":"10.1145\/2740908.2742024"},{"key":"18_CR25","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/978-3-319-08425-1_10","volume-title":"Theory and Practice of Digital Libraries \u2013 TPDL 2013 Selected Workshops","author":"T Giannakopoulos","year":"2014","unstructured":"Giannakopoulos, T., Stamatogiannakis, E., Foufoulas, I., Dimitropoulos, H., Manola, N., Ioannidis, Y.: Content visualization of scientific corpora using an extensible relational database implementation. In: Bolikowski, \u0141, Casarosa, V., Goodale, P., Houssos, N., Manghi, P., Schirrwagen, J. (eds.) TPDL 2013. CCIS, vol. 416, pp. 101\u2013112. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-08425-1_10"},{"key":"18_CR26","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/978-3-030-11226-4_27","volume-title":"Digital Libraries: Supporting Open Science","author":"T Giannakopoulos","year":"2019","unstructured":"Giannakopoulos, T., Foufoulas, Y., Dimitropoulos, H., Manola, N.: Interactive text analysis and information extraction. In: Manghi, P., Candela, L., Silvello, G. (eds.) IRCDL 2019. CCIS, vol. 988, pp. 340\u2013350. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11226-4_27"},{"key":"18_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/978-3-319-67008-9_28","volume-title":"Research and Advanced Technology for Digital Libraries","author":"Y Foufoulas","year":"2017","unstructured":"Foufoulas, Y., Stamatogiannakis, L., Dimitropoulos, H., Ioannidis, Y.: High-pass text filtering for citation matching. In: Kamps, J., Tsakonas, G., Manolopoulos, Y., Iliadis, L., Karydis, I. (eds.) TPDL 2017. LNCS, vol. 10450, pp. 355\u2013366. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-67008-9_28"},{"key":"18_CR28","unstructured":"Zhao, F., et al.: Hybrid querying over relational databases and large language models. In: CIDR (2025)"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, X., Sun, Z., Li, G.: Db-gpt Large language model meets database. Data Sci. Eng. 9, 102\u2013111 (2024)","DOI":"10.1007\/s41019-023-00235-6"},{"key":"18_CR30","unstructured":"Introducing the prompt() Function: Use the Power of LLMs with SQL. https:\/\/motherduck.com\/blog\/sql-llm-prompt-function-gpt-models"},{"key":"18_CR31","unstructured":"Liu, S., et al.: Optimizing LLM Queries in Relational Workloads. arXiv preprint arXiv:2403.05821v1 (2024)"},{"key":"18_CR32","doi-asserted-by":"publisher","unstructured":"Schindler, D., et al.: SoMeSci: a 5 star open data gold standard knowledge graph of software mentions in scientific articles. In: CIKM 2021, pp. 4574-458. https:\/\/doi.org\/10.1145\/3459637.3482017","DOI":"10.1145\/3459637.3482017"},{"key":"18_CR33","doi-asserted-by":"publisher","unstructured":"Parkin, M.. How JATS supports data integration: extracting data availability statements and funding information from research articles in Europe PMC. In: JATS-Con (2019). https:\/\/doi.org\/10.6084\/m9.figshare.8159426.v1","DOI":"10.6084\/m9.figshare.8159426.v1"},{"issue":"5","key":"18_CR34","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0250887","volume":"16","author":"LA McGuinness","year":"2021","unstructured":"McGuinness, L.A., Sheppard, A.S.: A descriptive analysis of the data availability statements accompanying medrxiv preprints and a comparison with their published counterparts. PLoS ONE 16(5), e0250887 (2021)","journal-title":"PLoS ONE"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Heddes, J., et al.: The automatic detection of dataset names in scientific articles. J. Inform. Sci. 6(8) (2021)","DOI":"10.3390\/data6080084"},{"key":"18_CR36","doi-asserted-by":"publisher","unstructured":"Polak, M.P., Morgan, D.: Extracting accurate materials data from research papers with conversational language models and prompt engineering. Nat. Commun. 15, 1569 (2024). https:\/\/doi.org\/10.1038\/s41467-024-45914-8","DOI":"10.1038\/s41467-024-45914-8"},{"key":"18_CR37","unstructured":"Kaggle. Make Data Count: Finding Data References. https:\/\/www.kaggle.com\/competitions\/make-data-count-finding-data-references (2024). Accessed June 2025"},{"key":"18_CR38","unstructured":"Yannis, F., et al.: LLM-Enhanced DETEXA Workflow Builder for Semantic Enrichment, TPDL (2025)"},{"key":"18_CR39","unstructured":"Etienne, V.-G., et al.: Annex A - Bibliometric Technical Report for the Study from Intent to Impact: Investigating the Effects of Open Sharing Commitments. Zenodo. https:\/\/zenodo.org\/records\/6643492"},{"key":"18_CR40","unstructured":"DETEXA source code. https:\/\/github.com\/madgik\/detexa"},{"key":"18_CR41","unstructured":"Implementation of the scalar UDF LLM_extract. https:\/\/github.com\/madgik\/detexa\/blob\/main\/DETEXA\/functions\/row\/llm.py"},{"key":"18_CR42","unstructured":"UK Reproducibility Network (UKRN), Open Research Indicators Project (2024). https:\/\/www.ukrn.org\/open-research-indicators\/"}],"container-title":["Communications in Computer and Information Science","New Trends in Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06136-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T18:38:06Z","timestamp":1758911886000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06136-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"ISBN":["9783032061355","9783032061362"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06136-2_18","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"27 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors\u00a0have no competing interests to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tampere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tpdl2025.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}