{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T10:05:25Z","timestamp":1713953125267},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,1,15]],"date-time":"2018-01-15T00:00:00Z","timestamp":1515974400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10772-018-9489-6","type":"journal-article","created":{"date-parts":[[2018,1,15]],"date-time":"2018-01-15T10:41:29Z","timestamp":1516012889000},"page":"621-628","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Unsupervised learning blocking keys technique for indexing Arabic entity resolution"],"prefix":"10.1007","volume":"22","author":[{"given":"Marwah","family":"Alian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arafat","family":"Awajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bandan","family":"Ramadan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,1,15]]},"reference":[{"key":"9489_CR1","unstructured":"Attia, M. (1999). A large scale computational processor of Arabic morphology and applications. Master\u2019s Dissertation, Computer Engineering. Egypt: Cairo University."},{"key":"9489_CR2","unstructured":"Ramadan, B. (2016). Indexing techniques for Real-time entity resolution on large dynamic databases, PhD Thesis, Ed.: Australian National University."},{"key":"9489_CR3","unstructured":"Ramadan, B., Christen, P. (2014). Forest-based dynamic sorted neighborhood indexing for real-time entity resolution, in Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, Shanghai, pp.\u00a01787\u20131790."},{"key":"9489_CR4","unstructured":"Chelli, A. (2016). ASem Light Stemmer, available at: \n                    http:\/\/www.arabicstemmer.com\/\n                    \n                  ."},{"key":"9489_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data matching: Concepts and techniques for record link-age, entity resolution, and duplicate detection","author":"P Christen","year":"2012","unstructured":"Christen, P. (2012). Data matching: Concepts and techniques for record link-age, entity resolution, and duplicate detection. New York: Springer."},{"issue":"9","key":"9489_CR6","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/TKDE.2011.127","volume":"24","author":"P Christen","year":"2012","unstructured":"Christen, P. (2012). A survey of indexing techniques for scalable record linkage and deduplication. IEEE Transactions on Knowledge and Data Engineering, 24(9), 1537\u20131555.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"9489_CR7","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/978-3-540-44918-8_6","volume-title":"Quality measures in data mining, ser. studies in computational intelligence","author":"P Christen","year":"2007","unstructured":"Christen, P., & Goiser, K. (2007). Quality and complexity measures for data linkage and deduplication, In Hamilton, F., Guillet, H. J. (Ed.) Quality measures in data mining, ser. studies in computational intelligence, New York: Springer, pp.\u00a0127\u2013151."},{"key":"9489_CR8","unstructured":"Farghaly, A. F. (1987). Three level morphology for Arabic,\u201d in the Arabic Morphology Workshop (AMW\u201987), Italy."},{"issue":"328","key":"9489_CR9","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"I Fellegi","year":"1969","unstructured":"Fellegi, I., & Sunter, A. (1969). A theory for record linkage. Journal of the American Statistical Association, 64(328), 1183\u20131210.","journal-title":"Journal of the American Statistical Association"},{"key":"9489_CR10","unstructured":"Al Ameed, H. K., Al Ketbi, S. O., Al Kaabi, A. A., Al Shebli, K. S. A., Al Shamsi, N. F., Al Nuaimi, N. H., Al Muhairi S. S., (2005). Arabic Light Stemmer: Anew Enhanced Approach,\u201d in The Second International Conference on Innovations in Information Technology (IIT\u201905),, pp.\u00a01\u20139."},{"issue":"1","key":"9489_CR11","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1023\/A:1009761603038","volume":"2","author":"MA Hernandez","year":"1998","unstructured":"Hernandez, M. A., & Stolfo, S. J. (1998). Real-world data is dirty: Data cleansing and the merge\/purge problem. Data Mining and Knowledge Discovery, 2(1): 9\u201337.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"9489_CR12","doi-asserted-by":"publisher","unstructured":"Alian, M., Al-Naymat, G., Ramadan B. (2017). Using transliteration with entity resolution for Arabic datasets, in 14th ACS\/IEEE International Conference on Computer Systems and Applications (AICCSA\u20192017), Hammamet, Tunisia, 2017, pp. 593\u2013597. \n                    https:\/\/doi.org\/10.1109\/AICCSA.2017.11\n                    \n                  .","DOI":"10.1109\/AICCSA.2017.11"},{"key":"9489_CR13","unstructured":"Kejriwal M., Miranker, D. P. (2013). An unsupervised algorithm for learning blocking schemes, in 2013 IEEE 13th International Conference on Data Mining, pp.\u00a0340\u2013349."},{"key":"9489_CR14","unstructured":"Bilenko, M., Kamath, B., Mooney, R. J. (2006). Adaptive blocking: Learning to scale up record linkage, in Sixth IEEE International Conference on Data Mining (ICDM-06), Hong Kong, pp.\u00a087\u201396."},{"key":"9489_CR15","doi-asserted-by":"crossref","unstructured":"Christen, P., Gayler, R., & Hawking, D. (2009). Similarity-aware indexing for real-time entity resolution. in 18th ACM conference on Information and knowledge management, Hong Kong, China, pp.\u00a01565\u20131568.","DOI":"10.1145\/1645953.1646173"},{"key":"9489_CR16","unstructured":"Ramadan, B., & Christen, P. (2015). Unsupervised blocking key selection for real-time entity resolution in advances in knowledge discovery and data mining PAKDD 2015. Lecture Notes in Computer Science, Cham, Vol.\u00a09078, pp.\u00a0574\u2013585."},{"key":"9489_CR17","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/978-3-642-40319-4_5","volume-title":"The series of lecture notes in computer science,trends and applications in knowledge discovery and data mining","author":"B Ramadan","year":"2013","unstructured":"Ramadan, B., Christen, P., Liang, H., & Gayler, R. W. (2013). Dynamic similarity-aware inverted indexing for real-time entity resolution in The series of lecture notes in computer science,trends and applications in knowledge discovery and data mining. New York: Springer, Vol.\u00a07867, pp.\u00a047\u201358."},{"issue":"4","key":"9489_CR18","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1145\/1644879.1644881","volume":"8","author":"A Farghaly","year":"2009","unstructured":"Farghaly, A., Shaalan, K. (2009). Arabic natural language processing: Challenges and solutions. ACM Transactions on Asian Language Information Processing, 8(4), 22.","journal-title":"ACM Transactions on Asian Language Information Processing"},{"key":"9489_CR19","unstructured":"Tran, K. N., Vatsalan, D., Christen, P., (2013). GeCo\u2014An online personal data Generator and Corruptor, in ACM Conference on Information and Knowledge Management (ICIKM\u201913), San Francisco, CA, USA, pp.\u00a02473\u20132475, \n                    http:\/\/dmm.anu.edu.au\/geco\n                    \n                  ."},{"key":"9489_CR20","unstructured":"Vogel, T., Naumann, F. (2012). Automatic blocking key selection for duplicate detection based on unigram combinations, in the international workshop on quality in databases (QDB)."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-9489-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9489-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9489-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,11]],"date-time":"2019-09-11T16:31:32Z","timestamp":1568219492000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-9489-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1,15]]},"references-count":20,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["9489"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-9489-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1,15]]},"assertion":[{"value":"12 October 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}