{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T14:13:41Z","timestamp":1658326421439},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,1,3]],"date-time":"2017-01-03T00:00:00Z","timestamp":1483401600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Datenbank Spektrum"],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1007\/s13222-016-0239-0","type":"journal-article","created":{"date-parts":[[2017,1,3]],"date-time":"2017-01-03T12:56:29Z","timestamp":1483448189000},"page":"69-76","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Das Fachgebiet \u201eInformationssysteme\u201c am Hasso-Plattner-Institut"],"prefix":"10.1007","volume":"17","author":[{"given":"Felix","family":"Naumann","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ralf","family":"Krestel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,1,3]]},"reference":[{"key":"239_CR1","first-page":"1198","volume-title":"Proceedings of the International Conference on Data Engineering (ICDE)","author":"Z Abedjan","year":"2014","unstructured":"Abedjan Z, Gruetze T, Jentzsch A, Naumann F (2014) Profiling and mining RDF data with ProLOD. In: Proceedings of the International Conference on Data Engineering (ICDE). IEEE Computer Society, Washington DC, S\u00a01198\u20131201 (Demo)"},{"issue":"4","key":"239_CR2","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1007\/s00778-015-0389-y","volume":"24","author":"Z Abedjan","year":"2015","unstructured":"Abedjan Z, Golab L, Naumann F (2015) Profiling relational data: a\u00a0survey. VLDB J 24(4):557\u2013581","journal-title":"VLDB J"},{"key":"239_CR3","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1145\/336597.336644","volume-title":"Proceedings of the ACM Conference on Digital Libraries","author":"E Agichtein","year":"2000","unstructured":"Agichtein E, Gravano L (2000) Snowball: extracting relations from large plain-text collections. In: Proceedings of the ACM Conference on Digital Libraries. ACM, New York, S 85\u201394"},{"key":"239_CR4","volume-title":"Challenges and opportunities with Big Data. Technical report, Computing Community Consortium","author":"D Agrawal","year":"2012","unstructured":"Agrawal D, Bernstein P, Bertino E, Davidson S, Dayal U, Franklin M, Widom J et\u00a0al (2012) Challenges and opportunities with Big Data. Technical report, Computing Community Consortium. http:\/\/cra.org\/ccc\/docs\/init\/bigdatawhitepaper.pdf . Zugegriffen: 1.1.2017"},{"key":"239_CR5","first-page":"1073","volume-title":"Proceedings of the International Conference on Data Engineering (ICDE)","author":"U Draisbach","year":"2012","unstructured":"Draisbach U, Naumann F, Szott S, Wonneberg O (2012) Adaptive windows for duplicate detection. In: Proceedings of the International Conference on Data Engineering (ICDE). IEEE Computer Society, Washington DC, S\u00a01073\u20131083"},{"key":"239_CR6","first-page":"299","volume-title":"Proceedings of the Conference Lernen, Wissen, Daten, Analysen (LWDA)","author":"C Godde","year":"2016","unstructured":"Godde C, Lazaridou K, Krestel R (2016) Classification of German newspaper comments. In: Proceedings of the Conference Lernen, Wissen, Daten, Analysen (LWDA). Hasso Plattner Institut, Potsdam, S\u00a0299\u2013310"},{"key":"239_CR7","doi-asserted-by":"crossref","unstructured":"Gruetze T, Yao G, Krestel R (2015) Learning temporal tagging behaviour. In: Proceedings of the Temporal Web Analytics Workshop (TempWeb) at the International World Wide Web Conference (WWW). ACM, New York, S\u00a01333\u20131338","DOI":"10.1145\/2740908.2741701"},{"key":"239_CR8","first-page":"213","volume-title":"Proceedings of the 21st International Conference on Applications of Natural Language to Information Systems (NLDB)","author":"T Gruetze","year":"2016","unstructured":"Gruetze T, Krestel R, Naumann F (2016) Topic shifts in StackOverflow: ask it like Socrates. In: Proceedings of the 21st International Conference on Applications of Natural Language to Information Systems (NLDB), Bd. 9612. Springer, Heidelberg, S\u00a0213\u2013221"},{"issue":"1","key":"239_CR9","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1023\/A:1009761603038","volume":"2","author":"MA Hern\u00e1ndez","year":"1998","unstructured":"Hern\u00e1ndez MA, Stolfo SJ (1998) Real-world data is dirty: data cleansing and the merge\/purge problem. Data Min Knowl Discov 2(1):9\u201337","journal-title":"Data Min Knowl Discov"},{"issue":"2","key":"239_CR10","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1093\/comjnl\/42.2.100","volume":"42","author":"Y Huhtala","year":"1999","unstructured":"Huhtala Y, K\u00e4rkk\u00e4inen J, Porkka P, Toivonen H (1999) TANE: an efficient algorithm for discovering functional and approximate dependencies. Comput J 42(2):100\u2013111","journal-title":"Comput J"},{"issue":"11","key":"239_CR11","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.14778\/2809974.2809975","volume":"8","author":"H K\u00f6hler","year":"2015","unstructured":"K\u00f6hler H, Link S, Zhou X (2015) Possible and certain SQL keys. Proceedings VLDB Endowment 8(11):1118\u20131129","journal-title":"Proceedings VLDB Endowment"},{"key":"239_CR12","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1145\/2187980.2188120","volume-title":"Proceedings of the International World Wide Web Conference (WWW)","author":"R Krestel","year":"2012","unstructured":"Krestel R, Wall A, Nejdl W (2012) Treehugger or Petrolhead? Identifying bias by comparing online news articles with political speeches. In: Proceedings of the International World Wide Web Conference (WWW). ACM, New York, S\u00a0547\u2013548"},{"key":"239_CR13","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1145\/2740908.2742716","volume-title":"Proceedings of the International World Wide Web Conference (WWW)","author":"R Krestel","year":"2015","unstructured":"Krestel R, Werkmeister T, Wiradarma TP, Kasneci G (2015) Tweet-recommender: finding relevant tweets for news articles. In: Proceedings of the International World Wide Web Conference (WWW). ACM, New York, S 53\u201354"},{"key":"239_CR14","doi-asserted-by":"crossref","unstructured":"Kruse S, Jentzsch A, Papenbrock T, Kaoudi Z, Quiane-Ruiz JA, Naumann F (2016) RDfind: scalable conditional inclusion dependency discovery in RDF datasets. In: Proceedings of the International Conference on Management of Data (SIGMOD). ACM, New York, S 953\u2013967","DOI":"10.1145\/2882903.2915206"},{"key":"239_CR15","first-page":"1679","volume-title":"Proceedings of the International Conference on Information and Knowledge Management (CIKM)","author":"D Lange","year":"2011","unstructured":"Lange D, Naumann F (2011) Efficient similarity search: arbitrary similarity measures, arbitrary composition. In: Proceedings of the International Conference on Information and Knowledge Management (CIKM). ACM, New York, S\u00a01679\u20131688"},{"issue":"12","key":"239_CR16","doi-asserted-by":"crossref","first-page":"1860","DOI":"10.14778\/2824032.2824086","volume":"8","author":"T Papenbrock","year":"2015","unstructured":"Papenbrock T, Bergmann T, Finke M, Zwiener J, Naumann F (2015) Data profiling with Metanome (demo). Proceedings VLDB Endowment 8(12):1860\u20131871","journal-title":"Proceedings VLDB Endowment"},{"issue":"10","key":"239_CR17","doi-asserted-by":"crossref","first-page":"1082","DOI":"10.14778\/2794367.2794377","volume":"8","author":"T Papenbrock","year":"2015","unstructured":"Papenbrock T, Ehrlich J, Marten J, Neubert T, Rudolph JP, Sch\u00f6nberg M, Zwiener J, Naumann F (2015) Functional dependency discovery: an experimental evaluation of seven algorithms. Proceedings VLDB Endowment 8(10):1082\u20131093","journal-title":"Proceedings VLDB Endowment"},{"key":"239_CR18","volume-title":"Proc. der Fachtagung Business, Technologie und Web (BTW)","author":"T Papenbrock","year":"2017","unstructured":"Papenbrock T, Naumann F (2017) A\u00a0hybrid approach for efficient unique column combination discovery. In: Proc. der Fachtagung Business, Technologie und Web (BTW). GI, Bonn, Deutschland (accepted)"},{"key":"239_CR19","first-page":"698","volume-title":"Scholarly Big Data: AI Perspectives, Challenges, and Ideas, Workshop at AAAI","author":"J Park","year":"2016","unstructured":"Park J, Blume-Kohout M, Krestel R, Nalisnick E, Smyth P (2016) Analyzing NIH funding patterns over time with statistical text analysis. In: Scholarly Big Data: AI Perspectives, Challenges, and Ideas, Workshop at AAAI. AAAI Press, Palo Alto, CA, S 698\u2013704"},{"issue":"2","key":"239_CR20","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.14778\/1454159.1454165","volume":"1","author":"M Weis","year":"2008","unstructured":"Weis M, Naumann F, Jehle U, Lufter J, Schuster H (2008) Industry-scale duplicate detection. Proceedings VLDB Endowment 1(2):1253\u20131264","journal-title":"Proceedings VLDB Endowment"},{"key":"239_CR21","first-page":"2075","volume-title":"Proceedings of the International Conference on Computational Linguistics (COLING)","author":"Z Zuo","year":"2014","unstructured":"Zuo Z, Kasneci G, Gruetze T, Naumann F (2014) BEL: bagging for entity linking. In: Proceedings of the International Conference on Computational Linguistics (COLING). ACL, Stroudsburg, PA, 2075\u20132086"}],"container-title":["Datenbank-Spektrum"],"original-title":[],"language":"de","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13222-016-0239-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13222-016-0239-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13222-016-0239-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T13:36:32Z","timestamp":1658324192000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13222-016-0239-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,3]]},"references-count":21,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,3]]}},"alternative-id":["239"],"URL":"https:\/\/doi.org\/10.1007\/s13222-016-0239-0","relation":{},"ISSN":["1618-2162","1610-1995"],"issn-type":[{"value":"1618-2162","type":"print"},{"value":"1610-1995","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,1,3]]}}}