{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T11:09:48Z","timestamp":1772363388905,"version":"3.50.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031887130","type":"print"},{"value":"9783031887147","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-88714-7_36","type":"book-chapter","created":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T11:35:10Z","timestamp":1743852910000},"page":"372-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Test Collection for\u00a0Dataset Retrieval"],"prefix":"10.1007","author":[{"given":"Nikolay","family":"Kolyada","sequence":"first","affiliation":[]},{"given":"Martin","family":"Potthast","sequence":"additional","affiliation":[]},{"given":"Benno","family":"Stein","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,4]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Brickley, D., Burgess, M., Noy, N.: Google dataset search: building a search engine for datasets in an open web ecosystem. In: The World Wide Web Conference, WWW 2019, pp. 1365\u20131375. Association for Computing Machinery, New York (May 2019)","DOI":"10.1145\/3308558.3313685"},{"issue":"2","key":"36_CR2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/792550.792552","volume":"36","author":"A Broder","year":"2002","unstructured":"Broder, A.: A taxonomy of web search. SIGIR Forum 36(2), 3\u201310 (2002)","journal-title":"SIGIR Forum"},{"issue":"12","key":"36_CR3","doi-asserted-by":"crossref","first-page":"2791","DOI":"10.14778\/3476311.3476346","volume":"14","author":"S Castelo","year":"2021","unstructured":"Castelo, S., Rampin, R., Santos, A., Bessa, A., Chirigati, F., Freire, J.: Auctus: a dataset search engine for data discovery and augmentation. Proc. VLDB Endowment 14(12), 2791\u20132794 (2021)","journal-title":"Proc. VLDB Endowment"},{"issue":"1","key":"36_CR4","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1007\/s00778-019-00564-x","volume":"29","author":"A Chapman","year":"2020","unstructured":"Chapman, A., et al.: Dataset search: a survey. VLDB J. 29(1), 251\u2013272 (2020)","journal-title":"VLDB J."},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Q., Chen, J., Zhou, X., Cheng, G.: Enhancing dataset search with compact data snippets. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, New York, NY, USA (Jul 2024)","DOI":"10.1145\/3626772.3657837"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Cleverdon, C.: The cranfield tests on index language devices. In: Aslib Proceedings, vol.\u00a019, pp. 173\u2013194, MCB UP Ltd (1967)","DOI":"10.1108\/eb050097"},{"key":"36_CR7","doi-asserted-by":"publisher","unstructured":"Cohen, T., et al.: A publicly available benchmark for biomedical dataset retrieval: the reference standard for the 2016 biocaddie dataset retrieval challenge. Database J. Biol. Databases Curation 2017, bax061 (2017). https:\/\/doi.org\/10.1093\/DATABASE\/BAX061","DOI":"10.1093\/DATABASE\/BAX061"},{"issue":"1","key":"36_CR8","doi-asserted-by":"crossref","first-page":"145","DOI":"10.5195\/jmla.2018.280","volume":"106","author":"S Fricke","year":"2018","unstructured":"Fricke, S.: Semantic scholar. J. Med. Libr. Assoc. 106(1), 145 (2018)","journal-title":"J. Med. Libr. Assoc."},{"issue":"4","key":"36_CR9","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1177\/0165551519837182","volume":"46","author":"KM Gregory","year":"2020","unstructured":"Gregory, K.M., Cousijn, H., Groth, P., Scharnhorst, A., Wyatt, S.: Understanding data search as a socio-technical practice. J. Inf. Sci. Eng. 46(4), 459\u2013475 (2020)","journal-title":"J. Inf. Sci. Eng."},{"key":"36_CR10","doi-asserted-by":"publisher","unstructured":"Guha, R.V., Brickley, D., Macbeth, S.: Schema.org: Evolution of structured data on the web. Commun. ACM 59(2), 44?51 (2016). https:\/\/doi.org\/10.1145\/2844544, ISSN 0001-0782","DOI":"10.1145\/2844544"},{"key":"36_CR11","unstructured":"Jacobsen, A., et\u00a0al.: Fair principles: interpretations and implementation considerations (2020)"},{"key":"36_CR12","unstructured":"Jiang, A.Q., et al.: Mistral 7B. arXiv [cs.CL] (Oct 2023)"},{"key":"36_CR13","doi-asserted-by":"publisher","unstructured":"Jiang, S., Hagelien, T.F., Natvig, M.K., Li, J.: Ontology-based semantic search for open government data. In: 13th IEEE International Conference on Semantic Computing, ICSC 2019, Newport Beach, 30 January - 1 February 2019, CA, USA, pp. 7\u201315, IEEE, Newport Beach, CA, USA (2019). https:\/\/doi.org\/10.1109\/ICOSC.2019.8665522","DOI":"10.1109\/ICOSC.2019.8665522"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Kacprzak, E., Koesten, L., Tennison, J., Simperl, E.: Characterising dataset search queries. In: Companion Proceedings of the The Web Conference 2018, WWW 2018, pp. 1485\u20131488. International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE (Apr 2018)","DOI":"10.1145\/3184558.3191597"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Stroudsburg, PA, USA (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"36_CR16","doi-asserted-by":"publisher","unstructured":"Kato, M.P., Ohshima, H., Liu, Y., Chen, H.O.: A test collection for ad-hoc dataset retrieval. In: Diaz, F., Shah, C., Suel, T., Castells, P., Jones, R., Sakai, T. (eds.) SIGIR 2021: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, 11-15 July 2021, Canada, pp. 2450\u20132456. ACM, Virtual Event, Canada (2021). https:\/\/doi.org\/10.1145\/3404835.3463261","DOI":"10.1145\/3404835.3463261"},{"key":"36_CR17","doi-asserted-by":"publisher","unstructured":"Khattab, O., Zaharia, M.: Colbert: efficient and effective passage search via contextualized late interaction over BERT. In: Huang, J.X., et al. (eds.) Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020, 25-30 July, Virtual Event, China, 2020, pp. 39\u201348, ACM, Virtual Event, China (2020). https:\/\/doi.org\/10.1145\/3397271.3401075, URL https:\/\/doi.org\/10.1145\/3397271.3401075","DOI":"10.1145\/3397271.3401075"},{"key":"36_CR18","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijhcs.2019.10.004","volume":"135","author":"L Koesten","year":"2020","unstructured":"Koesten, L., Simperl, E., Blount, T., Kacprzak, E., Tennison, J.: Everything you always wanted to know about a dataset: studies in data summarisation. Int. J. Hum Comput Stud. 135, 102367 (2020)","journal-title":"Int. J. Hum Comput Stud."},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Koesten, L.M., Kacprzak, E., Tennison, J.F.A., Simperl, E.: The trials and tribulations of working with structured data: -a study on information seeking behaviour. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, CHI 2017, pp. 1277\u20131289. Association for Computing Machinery, New York (May 2017)","DOI":"10.1145\/3025453.3025838"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Li, H., Councill, I., Lee, W.C., Giles, C.L.: CiteSeerx: an architecture and web service design for an academic document search engine. In: Proceedings of the 15th international conference on World Wide Web, WWW 2006, pp. 883\u2013884. Association for Computing Machinery, New York (May 2006)","DOI":"10.1145\/1135777.1135926"},{"key":"36_CR21","doi-asserted-by":"publisher","unstructured":"Lin, T., et al.: ACORDAR: a test collection for ad hoc content-based (RDF) dataset retrieval. In: Amig\u00f3, E., Castells, P., Gonzalo, J., Carterette, B., Culpepper, J.S., Kazai, G. (eds.) SIGIR 2022: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, 11 - 15 July 2022, Madrid, Spain, pp. 2981\u20132991. ACM, Madrid, Spain (2022). https:\/\/doi.org\/10.1145\/3477495.3531729","DOI":"10.1145\/3477495.3531729"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"L\u00f6ffler, F., Schuldt, A., K\u00f6nig-Ries, B., Bruelheide, H., Klan, F.: A test collection for dataset retrieval in biodiversity research. Res. Ideas Outcomes 7 (May 2021)","DOI":"10.3897\/rio.7.e67887"},{"key":"36_CR23","unstructured":"Maali, F., Erickson, J., Archer, P.: Data catalog vocabulary (dcat). In: w3c recommendation. World Wide Web Consortium, pp. 29\u2013126 (2014)"},{"key":"36_CR24","doi-asserted-by":"publisher","unstructured":"Macdonald, C., Tonellotto, N.: Declarative experimentation in information retrieval using pyterrier. In: Balog, K., Setty, V., Lioma, C., Liu, Y., Zhang, M., Berberich, K. (eds.) ICTIR 2020: The 2020 ACM SIGIR International Conference on the Theory of Information Retrieval, Virtual Event, Norway, September 14-17, 2020, pp. 161\u2013168, ACM, Virtual Event, Norway (2020). https:\/\/doi.org\/10.1145\/3409256.3409829","DOI":"10.1145\/3409256.3409829"},{"key":"36_CR25","doi-asserted-by":"crossref","unstructured":"Maier, D., Megler, V.M., Tufte, K.: Challenges for dataset search (2014)","DOI":"10.1007\/978-3-319-05810-8_1"},{"issue":"4","key":"36_CR26","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1017\/S1351324921000127","volume":"28","author":"M Martinc","year":"2022","unstructured":"Martinc, M., \u0160krlj, B., Pollak, S.: KID: Transformer-based neural tagger for keyword identification. Nat. Lang. Eng. 28(4), 409\u2013448 (2022)","journal-title":"Nat. Lang. Eng."},{"issue":"1","key":"36_CR27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2964909","volume":"8","author":"S Neumaier","year":"2016","unstructured":"Neumaier, S., Umbrich, J., Polleres, A.: Automated quality assessment of metadata across open data portals. J. Data Inform. Quality 8(1), 1\u201329 (2016)","journal-title":"J. Data Inform. Quality"},{"issue":"2","key":"36_CR28","doi-asserted-by":"crossref","first-page":"206","DOI":"10.5860\/crln.62.2.206","volume":"62","author":"E Pentz","year":"2001","unstructured":"Pentz, E.: Crossref: the missing link. College Res. Libraries News 62(2), 206\u2013228 (2001)","journal-title":"College Res. Libraries News"},{"key":"36_CR29","doi-asserted-by":"publisher","unstructured":"Viswanathan, V., Gao, L., Wu, T., Liu, P., Neubig, G.: Datafinder: Scientific dataset recommendation from natural language descriptions. In: Rogers, A., Boyd-Graber, J.L., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, 9-14 July 2023, Toronto, Canada, pp. 10288\u201310303. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/V1\/2023.ACL-LONG.573","DOI":"10.18653\/V1\/2023.ACL-LONG.573"},{"issue":"1","key":"36_CR30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2016.18","volume":"3","author":"MD Wilkinson","year":"2016","unstructured":"Wilkinson, M.D., et al.: The fair guiding principles for scientific data management and stewardship. Sci. Data 3(1), 1\u20139 (2016)","journal-title":"Sci. Data"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-88714-7_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T11:35:51Z","timestamp":1743852951000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88714-7_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031887130","9783031887147"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88714-7_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"4 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lucca","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"47","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2025.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}