{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T22:07:53Z","timestamp":1769551673332,"version":"3.49.0"},"reference-count":23,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2020,11,10]],"date-time":"2020-11-10T00:00:00Z","timestamp":1604966400000},"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":["J. Data and Information Quality"],"published-print":{"date-parts":[[2020,12,31]]},"abstract":"<jats:p>\n            We present\n            <jats:italic>BLAST2<\/jats:italic>\n            , a novel technique to efficiently extract\n            <jats:italic>loose schema information<\/jats:italic>\n            , i.e., metadata that can serve as a surrogate of the schema alignment task within the Entity Resolution (ER) process, to identify records that refer to the same real-world entity when integrating multiple, heterogeneous, and voluminous data sources. The\n            <jats:italic>loose schema information<\/jats:italic>\n            is exploited for reducing the overall complexity of ER, whose na\u00efve solution would imply O(n\n            <jats:sup>2<\/jats:sup>\n            ) comparisons, where\n            <jats:italic>n<\/jats:italic>\n            is the number of entity representations involved in the process and can be extracted by both structured and unstructured data sources.\n            <jats:italic>BLAST2<\/jats:italic>\n            is completely unsupervised yet able to achieve almost the same precision and recall of supervised state-of-the-art schema alignment techniques when employed for Entity Resolution tasks, as shown in our experimental evaluation performed on two real-world datasets (composed of 7 and 10 data sources, respectively).\n          <\/jats:p>","DOI":"10.1145\/3394957","type":"journal-article","created":{"date-parts":[[2020,7,7]],"date-time":"2020-07-07T12:34:39Z","timestamp":1594125279000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["<i>BLAST2<\/i>"],"prefix":"10.1145","volume":"12","author":[{"given":"Domenico","family":"Beneventano","sequence":"first","affiliation":[{"name":"Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonia","family":"Bergamaschi","sequence":"additional","affiliation":[{"name":"Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5977-1078","authenticated-orcid":false,"given":"Luca","family":"Gagliardelli","sequence":"additional","affiliation":[{"name":"Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3466-509X","authenticated-orcid":false,"given":"Giovanni","family":"Simonini","sequence":"additional","affiliation":[{"name":"Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,11,10]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Proceedings of the 27th Italian Symposium on Advanced Database Systems, Castiglione della Pescaia (Grosseto\u201919)","author":"Beneventano Domenico","year":"2019"},{"key":"e_1_2_1_2_1","volume-title":"Handbook of Conceptual Modeling: Theory, Practice and Research Challenges","author":"Bergamaschi Sonia"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2005.126"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2472010"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3102254.3102259"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.127"},{"key":"e_1_2_1_7_1","unstructured":"Sanjib Das AnHai Doan Paul Suganthan G. C. Chaitanya Gokhale and Pradap Konda. [n.d.]. The Magellan Data Repository. Retrieved from https:\/\/sites.google.com\/site\/anhaidgroup\/useful-stuff\/data.  Sanjib Das AnHai Doan Paul Suganthan G. C. Chaitanya Gokhale and Pradap Konda. [n.d.]. The Magellan Data Repository. Retrieved from https:\/\/sites.google.com\/site\/anhaidgroup\/useful-stuff\/data."},{"key":"e_1_2_1_8_1","volume-title":"C","author":"Efthymiou Vasilis","year":"2017"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of the 22nd International Conference on Extending Database Technology (EDBT\u201919)","author":"Gagliardelli Luca","year":"2019"},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the 21st International Conference on Data Engineering (ICDE\u201918)","author":"Giovanni Simonini","year":"2018"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994535"},{"key":"e_1_2_1_12_1","volume-title":"Mining of Massive Datasets","author":"Leskovec Jure"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.150"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.54"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733085.2733098"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the 22nd International Conference on Extending Database Technology (EDBT\u201916)","author":"Papadakis George","year":"2016"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3385658.3385664"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93040-4_2"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.253"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994533"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2019.03.006"},{"key":"e_1_2_1_23_1","series-title":"Lecture Notes in Computer Science","volume-title":"Search Computing\u2014Trends and Developments","author":"Sorrentino Serena"}],"container-title":["Journal of Data and Information Quality"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394957","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:00Z","timestamp":1750193280000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394957"}},"subtitle":["An Efficient Technique for Loose Schema Information Extraction from Heterogeneous Big Data Sources"],"short-title":[],"issued":{"date-parts":[[2020,11,10]]},"references-count":23,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,12,31]]}},"alternative-id":["10.1145\/3394957"],"URL":"https:\/\/doi.org\/10.1145\/3394957","relation":{},"ISSN":["1936-1955","1936-1963"],"issn-type":[{"value":"1936-1955","type":"print"},{"value":"1936-1963","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,10]]},"assertion":[{"value":"2019-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-11-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}