{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:42:00Z","timestamp":1743100920262,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030864712"},{"type":"electronic","value":"9783030864729"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86472-9_4","type":"book-chapter","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T22:02:41Z","timestamp":1630360961000},"page":"35-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Tabular Metadata Location and\u00a0Classification in Large-Scale Structured\u00a0Datasets"],"prefix":"10.1007","author":[{"given":"Kazi","family":"Islam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Gubanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,31]]},"reference":[{"unstructured":"Census bureau. https:\/\/www.census.gov\/data\/datasets.html","key":"4_CR1"},{"key":"4_CR2","series-title":"Lecture Notes in Business Information Processing","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-642-03422-0_9","volume-title":"Business Intelligence for the Real-Time Enterprise","author":"B Alexe","year":"2009","unstructured":"Alexe, B., et al.: Simplifying information integration: object-based flow-of-mappings framework for integration. In: Castellanos, M., Dayal, U., Sellis, T. (eds.) BIRTE 2008. LNBIP, vol. 27, pp. 108\u2013121. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-03422-0_9"},{"key":"4_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-319-25264-3_18","volume-title":"Conceptual Modeling","author":"K Braunschweig","year":"2015","unstructured":"Braunschweig, K., Thiele, M., Lehner, W.: From web tables to concepts: a semantic normalization approach. In: Johannesson, P., Lee, M.L., Liddle, S.W., Opdahl, A.L., L\u00f3pez, \u00d3.P. (eds.) ER 2015. LNCS, vol. 9381, pp. 247\u2013260. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-25264-3_18"},{"doi-asserted-by":"crossref","unstructured":"Cafarella, M.J., Halevy, A., Wang, D.Z., Wu, E., Zhang, Y.: WebTables: exploring the power of tables on the web. In: VLDB (2008)","key":"4_CR4","DOI":"10.14778\/1453856.1453916"},{"unstructured":"Cafarella, M.J., Halevy, A., Zhang, Y., Wang, D., Wu, E.: Uncovering the relational web. In: WebDB (2008)","key":"4_CR5"},{"doi-asserted-by":"crossref","unstructured":"Chen, Z., Dadiomov, S., Wesley, R., Xiao, G., Cory, D., Cafarella, M., Mackinlay, J.: Spreadsheet property detection with rule-assisted active learning. In: CIKM. ACM (2017)","key":"4_CR6","DOI":"10.1145\/3132847.3132882"},{"unstructured":"Christodoulakis, C., Munson, E.B., Gabel, M., Brown, A.D., Miller, R.J.: Pytheas: pattern-based table discovery in CSV files. In: PVLDB, July 2020","key":"4_CR7"},{"doi-asserted-by":"crossref","unstructured":"Codd, E.F.: A relational model of data for large shared data banks. In: CACM. vol. 13, no. 6, June 1970","key":"4_CR8","DOI":"10.1145\/362384.362685"},{"doi-asserted-by":"crossref","unstructured":"Dong, X.L.: Challenges and innovations in building a product knowledge graph. In: KDD (2018)","key":"4_CR9","DOI":"10.1145\/3219819.3219938"},{"doi-asserted-by":"crossref","unstructured":"Fang, J., Mitra, P., Tang, Z., Giles, C.L.: Table header detection and classification. In: AAAI, vol. 26, no. 1, July 2012","key":"4_CR10","DOI":"10.1609\/aaai.v26i1.8206"},{"unstructured":"Gentile, A.L., Ristoski, P., Eckel, S., Ritze, D., Paulheim, H.: Entity matching on web tables: a table embeddings approach for blocking. In: EDBT (2017)","key":"4_CR11"},{"unstructured":"Gol, M.G., Pujara, J., Szekely, P.: Tabular cell classification using pre-trained cell embeddings. In: ICDM (2019)","key":"4_CR12"},{"unstructured":"Gubanov, M.: Hybrid: a large-scale in-memory image analytics system. In: CIDR (2017)","key":"4_CR13"},{"doi-asserted-by":"crossref","unstructured":"Gubanov, M.: Polyfuse: a large-scale hybrid data fusion system. In: ICDE (2017)","key":"4_CR14","DOI":"10.1109\/ICDE.2017.230"},{"doi-asserted-by":"crossref","unstructured":"Gubanov, M., Priya, M., Podkorytov, M.: CognitiveDB: an intelligent navigator for large-scale dark structured data. In: WWW (2017)","key":"4_CR15","DOI":"10.1145\/3041021.3054735"},{"doi-asserted-by":"crossref","unstructured":"Gubanov, M., Pyayt, A.: READFAST: high-relevance search-engine for big text. In: ACM CIKM (2013)","key":"4_CR16","DOI":"10.1145\/2505515.2508215"},{"unstructured":"Gubanov, M., Pyayt, A.: Type-aware web search. In: EDBT (2014)","key":"4_CR17"},{"doi-asserted-by":"crossref","unstructured":"Gubanov, M.N., Popa, L., Ho, H., Pirahesh, H., Chang, J.-Y., Chen, S.-C.: IBM UFO repository: object-oriented data integration. In: VLDB (2009)","key":"4_CR18","DOI":"10.14778\/1687553.1687601"},{"doi-asserted-by":"crossref","unstructured":"Hancock, B., Lee, H., Yu, C.: Generating titles for web tables. In: WWW. ACM, New York (2019)","key":"4_CR19","DOI":"10.1145\/3308558.3313399"},{"doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","key":"4_CR20","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"4_CR21","volume-title":"Recurrent Neural Networks: Design and Applications","author":"LC Jain","year":"1999","unstructured":"Jain, L.C., Medsker, L.R.: Recurrent Neural Networks: Design and Applications, 1st edn. CRC Press Inc., Boca Raton (1999)","edition":"1"},{"doi-asserted-by":"crossref","unstructured":"Khan, R., Gubanov, M.: WebLens: towards interactive large-scale structured data profiling. In: CIKM. ACM (2020)","key":"4_CR22","DOI":"10.1145\/3340531.3417443"},{"unstructured":"Jiang, L., Vitagliano, G.: Structure detection in verbose CSV files. In: EDBT, March 2021","key":"4_CR23"},{"doi-asserted-by":"crossref","unstructured":"Lehmberg, O., Ritze, D., Meusel, R., Bizer, C.: A large public corpus of web tables containing time and context metadata. In: Bourdeau, J., Hendler, J., Nkambou, R., Horrocks, I., Zhao, B.Y. (eds.) WWW (2016)","key":"4_CR24","DOI":"10.1145\/2872518.2889386"},{"doi-asserted-by":"crossref","unstructured":"Limaye, G., Sarawagi, S., Chakrabarti, S.: Annotating and searching web tables using entities, types and relationships (2010)","key":"4_CR25","DOI":"10.14778\/1920841.1921005"},{"unstructured":"Mulwad, V., Finin, T., Joshi, A.: Generating linked data by inferring the semantics of tables. In: VLDS, CEUR Workshop. CEUR-WS.org (2011)","key":"4_CR26"},{"doi-asserted-by":"crossref","unstructured":"Ortiz, S., Enbatan, C., Podkorytov, M., Soderman, D., Gubanov, M.: Hybrid.json: high-velocity parallel in-memory polystore JSON ingest. In: IEEE Bigdata (2017)","key":"4_CR27","DOI":"10.1109\/BigData.2017.8258549"},{"doi-asserted-by":"crossref","unstructured":"Podkorytov, M., Soderman, D., Gubanov, M.N.: Hybrid.poly: an interactive large-scale in-memory analytical polystore. In: ICDM Workshops, pp. 43\u201350. IEEE Computer Society (2017)","key":"4_CR28","DOI":"10.1109\/ICDMW.2017.13"},{"unstructured":"Ritze, D., Bizer, C.: Matching web tables to DBpedia - a feature utility study. In: EDBT (2017)","key":"4_CR29"},{"doi-asserted-by":"crossref","unstructured":"Simmons, M., Armstrong, D., Soderman, D., Gubanov, M.: Hybrid.media: high velocity video ingestion in an in-memory scalable analytical polystore. In: IEEE Bigdata (2017)","key":"4_CR30","DOI":"10.1109\/BigData.2017.8258558"},{"doi-asserted-by":"crossref","unstructured":"Soderman, S., Kola, A., Podkorytov, M., Geyer, M., Gubanov, M.: Hybrid.AI: a learning search engine for large-scale structured data. In: WWW (2018)","key":"4_CR31","DOI":"10.1145\/3184558.3191600"},{"key":"4_CR32","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/978-981-13-2330-0_17","volume-title":"Geospatial Infrastructure, Applications and Technologies: India Case Studies","author":"A Subramanian","year":"2018","unstructured":"Subramanian, A., Srinivasa, S.: Semantic interpretation and integration of open data tables. In: Sarda, N.L., Acharya, P.S., Sen, S. (eds.) Geospatial Infrastructure, Applications and Technologies: India Case Studies, pp. 217\u2013233. Springer, Singapore (2018). https:\/\/doi.org\/10.1007\/978-981-13-2330-0_17"},{"doi-asserted-by":"crossref","unstructured":"Uhrig, R.: Introduction to artificial neural networks. In: IECON, vol. 1, pp. 33\u201337 (1995)","key":"4_CR33","DOI":"10.1109\/IECON.1995.483329"},{"doi-asserted-by":"crossref","unstructured":"Villasenor, S., Nguyen, T., Kola, A., Soderman, S., Gubanov, M.: Scalable spam classifier for web tables. In: IEEE Big Data (2017)","key":"4_CR34","DOI":"10.1109\/BigData.2017.8258564"},{"unstructured":"Wang, L.L., Lo, K., et al.: The covid-19 open research dataset. ArXiv (2020)","key":"4_CR35"},{"issue":"3","key":"4_CR36","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1142\/S0218194018500109","volume":"28","author":"N Wang","year":"2018","unstructured":"Wang, N., Ren, X.: Identifying multiple entity columns in web tables. Int. J. Softw. Eng. Knowl. Eng. 28(3), 287\u2013310 (2018)","journal-title":"Int. J. Softw. Eng. Knowl. Eng."},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Hu, J.: A machine learning based approach for table detection on the web. In: WWW 2002, pp. 242\u2013250. ACM, New York (2002)","key":"4_CR37","DOI":"10.1145\/511475.511478"}],"container-title":["Lecture Notes in Computer Science","Database and Expert Systems Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86472-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T12:24:16Z","timestamp":1725711856000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86472-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030864712","9783030864729"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86472-9_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"31 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DEXA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database and Expert Systems Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dexa2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.dexa.org\/dexa2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"149","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"DEXA 2021 Workshops: 50 papers submitted, 23 papers accepted","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}