{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:43:40Z","timestamp":1780058620832,"version":"3.54.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Singapore","isbn-type":[{"value":"9789813343696","type":"print"},{"value":"9789813343702","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-981-33-4370-2_6","type":"book-chapter","created":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T00:48:04Z","timestamp":1605746884000},"page":"78-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Py_ape: Text Data Acquiring, Extracting, Cleaning and Schema Matching in Python"],"prefix":"10.1007","author":[{"given":"Bich-Ngan T.","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phuong N. H.","family":"Ph\u1ea1m","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vu Thanh","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phan Quoc","family":"Viet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le Dinh","family":"Tuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vaclav","family":"Snasel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"6_CR1","unstructured":"Chen, C., Golshan, B., Halevy, A., Tan, W.-C., Doan, A.H.: BigGorilla: an open-source ecosystem for data preparation and integration. Comput. Sci. IEEE Data Eng. Bull. (2018)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Doan, A., Halevy, A., Ives, Z.: Principles of Data Integration, 1st edn. Morgan Kaufmann (2012)","DOI":"10.1016\/B978-0-12-416044-6.00001-6"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Golshan, B., Halevy, A.Y., Mihaila, G.A., Tan, W.: Data integration: after the teenage years. In: PODS (2017)","DOI":"10.1145\/3034786.3056124"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Miller, R.J.: The future of data integration. In: KDD, p. 3 (2017)","DOI":"10.1145\/3097983.3105809"},{"key":"6_CR5","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"6_CR6","first-page":"83","volume":"26","author":"A Doan","year":"2005","unstructured":"Doan, A., Halevy, A.Y.: Semantic integration research in the database community: a brief survey. AI Mag. 26(1), 83\u201394 (2005)","journal-title":"AI Mag."},{"key":"6_CR7","unstructured":"Pessig, P.: Entity matching using Magellan - matching drug reference tables. In: CPCP Retreat (2017). http:\/\/cpcp.wisc.edu\/resources\/cpcp-2017-retreat-entity-matching"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Mudgal, S., et al.: Deep learning for entity matching: a design space exploration. In: SIGMOD-18 (2018)","DOI":"10.1145\/3183713.3196926"},{"issue":"12","key":"6_CR9","first-page":"1197","volume":"9","author":"P Konda","year":"2016","unstructured":"Konda, P., et al.: Magellan: toward building entity matching management systems. PVLDB 9(12), 1197\u20131208 (2016)","journal-title":"PVLDB"},{"key":"6_CR10","unstructured":"Wang, S., Jiang, J.: A compare-aggregate model for matching text sequences. In: ICLR (2017)"},{"issue":"3","key":"6_CR11","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s11704-015-5900-5","volume":"10","author":"M Yu","year":"2016","unstructured":"Yu, M., et al.: String similarity search and join: a survey. Front. Comput. Sci. 10(3), 399\u2013417 (2016)","journal-title":"Front. Comput. Sci."},{"key":"6_CR12","unstructured":"Bloor Research International: Self-Service Data Preparation and Cataloguing (2016). https:\/\/www.bloorresearch.com\/research\/self-service-data-preparation-cataloguing\/. Accessed 14 May 2018"},{"key":"6_CR13","unstructured":"Heer, J., Hellerstein, J., Kandel, S.: Predictive interaction for data transformation. In: Proceedings of the Conference on Innovative Data Systems Research (CIDR) (2015)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Jin, Z., et al.: Foofah: transforming data by example. In: Proceedings of the 2017 ACM International Conference on Management of Data, pp. 683\u2013698. ACM (2017)","DOI":"10.1145\/3035918.3064034"},{"key":"6_CR15","unstructured":"Kopelowitz, T., Porat, E.: A simple algorithm for approximating the text-to-pattern hamming distance. In: 1st Symposium on Simplicity in Algorithms (SOSA 2018) (2018)"},{"key":"6_CR16","doi-asserted-by":"publisher","unstructured":"Ho, T., Oh, S., Kim, H.: New algorithms for fixed-length approximate string matching and approximate circular string matching under the Hamming distance. J. Supercomput. 74, 1815\u20131834 (2018). https:\/\/doi.org\/10.1007\/s11227-017-2192-6","DOI":"10.1007\/s11227-017-2192-6"},{"key":"6_CR17","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. JMLR 12, 2825\u20132830 (2011)","journal-title":"JMLR"},{"key":"6_CR18","unstructured":"Bernstein, P.A., Melnik, S.: Metadata management. In: Proceedings of the IEEE CS International Conference on Data Engineering. IEEE Computer Society (2004)"},{"key":"6_CR19","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/j.sysarc.2018.11.001","volume":"97","author":"S Mittal","year":"2019","unstructured":"Mittal, S., Nag, S.: A survey of encoding techniques for reducing data-movement energy. J. Syst. Arch. 97, 373\u2013396 (2019)","journal-title":"J. Syst. Arch."},{"key":"6_CR20","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.tcs.2016.01.023","volume":"638","author":"A Apostolico","year":"2016","unstructured":"Apostolico, A., et al.: Sequence similarity measures based on bounded hamming distance. Theoret. Comput. Sci. 638, 76\u201390 (2016)","journal-title":"Theoret. Comput. Sci."},{"key":"6_CR21","unstructured":"Gusfield, D.: Algorithms on Strings, Trees and Sequences: Computer Science and Computational Biology, pp. 125\u2013128. Cambridge University Press, Cambridge (1999). ISBN 0-521-58519-8"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Gomaa, W.H., Fahmy, A.A.: A survey of text similarity approaches. Int. J. Comput. Appl. (0975\u20138887). 68(13) (2013)","DOI":"10.5120\/11638-7118"},{"issue":"3","key":"6_CR23","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s11704-015-5900-5","volume":"10","author":"M Yu","year":"2015","unstructured":"Yu, M., Li, G., Deng, D., Feng, J.: String similarity search and join: a survey. Front. Comput. Sci. 10(3), 399\u2013417 (2015). https:\/\/doi.org\/10.1007\/s11704-015-5900-5","journal-title":"Front. Comput. Sci."},{"key":"6_CR24","unstructured":"Recruit Holdings Co., Ltd.: Recruit\u2019s Artificial Intelligence Laboratory Releases BigGorilla: An Open-source Data Integration and Data Preparation Ecosystem (2019). https:\/\/recruit-holdings.com\/news_data\/release\/2017\/0630_7890.html"}],"container-title":["Communications in Computer and Information Science","Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-33-4370-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,25]],"date-time":"2021-04-25T00:51:01Z","timestamp":1619311861000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-33-4370-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9789813343696","9789813343702"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-33-4370-2_6","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"19 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FDSE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Future Data and Security Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Quy Nhon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"fdse2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.thefdse.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"161","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":"53","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":"8","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":"33% - 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":"3","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":"5.5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5.5 avg. reviewers\/paper (for two submission rounds in total). LNCS 12466 includes 24 of the accepted papers and 2 invited keynotes. CCIS 1306 includes 29 full and 8 short of the accepted papers. The conference was held virtually due to the COVID-19 pandemic.","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)"}}]}}