{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T23:40:10Z","timestamp":1748821210337,"version":"3.41.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319320243"},{"type":"electronic","value":"9783319320250"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-32025-0_8","type":"book-chapter","created":{"date-parts":[[2016,3,24]],"date-time":"2016-03-24T12:47:38Z","timestamp":1458823658000},"page":"117-132","source":"Crossref","is-referenced-by-count":0,"title":["CTextEM: Using Consolidated Textual Data for Entity Matching"],"prefix":"10.1007","author":[{"given":"Qiang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binbin","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"An","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanfeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengpeng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,3,25]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Aizawa, A., Oyama, K.: A fast linkage detection scheme for multi-source information integration. In: Proceedings of International Workshop on Challenges in Web Information Retrieval and Integration, WIRI 2005, pp. 30\u201339 (2005)","DOI":"10.1109\/WIRI.2005.2"},{"key":"8_CR2","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"8_CR3","unstructured":"Borthwick, A., Goldberg, A., Cheung, P., Winkel, A.: Batch automated blocking and record matching (2011)"},{"issue":"9","key":"8_CR4","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/TKDE.2011.127","volume":"24","author":"P Christen","year":"2012","unstructured":"Christen, P.: A survey of indexing techniques for scalable record linkage and deduplication. Knowl. Data Eng. IEEE Trans. 24(9), 1537\u20131555 (2012)","journal-title":"Knowl. Data Eng. IEEE Trans."},{"key":"8_CR5","unstructured":"Das, Martins, D., A.F.T.: A survey on automatic text summarization. Int. J. Eng (2007)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Dhamankar, R., Lee, Y., Doan, A., Halevy, A., Domingos, P.: iMAP: discovering complex semantic matches between database schemas. In: Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 383\u2013394. ACM (2004)","DOI":"10.1145\/1007568.1007612"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Ektefa, M., Sidi, F., Ibrahim, H., Jabar, M.A., Memar, S., Ramli, A.: A threshold-based similarity measure for duplicate detection. In: IEEE Conference on Open Systems (ICOS), pp. 37\u201341. IEEE (2011)","DOI":"10.1109\/ICOS.2011.6079233"},{"issue":"1","key":"8_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2007","unstructured":"Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: a survey. IEEE Trans. Knowl. Data Eng. 19(1), 1\u201316 (2007)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"8_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1007\/978-3-642-23982-3_36","volume-title":"Web Information Systems and Mining","author":"C Gao","year":"2011","unstructured":"Gao, C., Hong, X., Peng, Z., Chen, H.: Web trace duplication detection based on context. In: Gong, Z., Luo, X., Chen, J., Lei, J., Wang, F.L. (eds.) WISM 2011, Part II. LNCS, vol. 6988, pp. 292\u2013301. Springer, Heidelberg (2011)"},{"issue":"1\u20132","key":"8_CR10","doi-asserted-by":"publisher","first-page":"417","DOI":"10.14778\/1920841.1920897","volume":"3","author":"S Guo","year":"2010","unstructured":"Guo, S., Dong, X.L., Srivastava, D., Zajac, R.: Record linkage with uniqueness constraints and erroneous values. Proc. VLDB Endowment 3(1\u20132), 417\u2013428 (2010)","journal-title":"Proc. VLDB Endowment"},{"key":"8_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/11926078_4","volume-title":"The Semantic Web - ISWC 2006","author":"J Hassell","year":"2006","unstructured":"Hassell, J., Aleman-Meza, B., Arpinar, I.B.: Ontology-driven automatic entity disambiguation in unstructured text. In: Cruz, I., Decker, S., Allemang, D., Preist, C., Schwabe, D., Mika, P., Uschold, M., Aroyo, L.M. (eds.) ISWC 2006. LNCS, vol. 4273, pp. 44\u201357. Springer, Heidelberg (2006)"},{"issue":"4","key":"8_CR12","first-page":"289","volume":"25","author":"T Hofmann","year":"1999","unstructured":"Hofmann, T.: Probabilistic latent semantic analysis. Proc. Uncertainty Artif. Intell. Uai 25(4), 289\u2013296 (1999)","journal-title":"Proc. Uncertainty Artif. Intell. Uai"},{"key":"8_CR13","unstructured":"Kim, D., Wang, H., Oh, A.: Context-dependent conceptualization. In: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, pp. 2654\u20132661. AAAI Press (2013)"},{"key":"8_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/978-3-642-34109-0_29","volume-title":"String Processing and Information Retrieval","author":"S-J Kim","year":"2012","unstructured":"Kim, S.-J., Lee, J.-H.: Method of mining subtopics using dependency structure and anchor texts. In: Calder\u00f3n-Benavides, L., Gonz\u00e1lez-Caro, C., Ch\u00e1vez, E., Ziviani, N. (eds.) SPIRE 2012. LNCS, vol. 7608, pp. 277\u2013283. Springer, Heidelberg (2012)"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Koudas, N., Sarawagi, S., Srivastava, D.: Record linkage: similarity measures and algorithms. In: Sigmod Conference, pp. 802\u2013803 (2006)","DOI":"10.1145\/1142473.1142599"},{"issue":"2","key":"8_CR16","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1080\/01638539809545028","volume":"25","author":"TK Landauer","year":"1998","unstructured":"Landauer, T.K., Foltz, P.W., Laham, D.: An introduction to latent semantic analysis. Discourse Process. 25(2), 259\u2013284 (1998). Special issue","journal-title":"Discourse Process."},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Maowen, W., Dong, Z.C., Weiyao, L., Qiang, W.Q.: Text topic mining based on LDA and co-occurrence theory. In: 7th International Conference on Computer Science & Education (ICCSE), pp. 525\u2013528. IEEE (2012)","DOI":"10.1109\/ICCSE.2012.6295129"},{"issue":"1","key":"8_CR18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2202\/1544-6115.1406","volume":"8","author":"E Parkhomenko","year":"2009","unstructured":"Parkhomenko, E., Tritchler, D., Beyene, J.: Sparse canonical correlation analysis with application to genomic data integration. Stat. Appl. Genet. Mol. Biol. 8(1), 1\u201334 (2009)","journal-title":"Stat. Appl. Genet. Mol. Biol."},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Sarwar, B., Karypis, G., Konstan, J., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th International Conference on World Wide Web, pp. 285\u2013295. ACM (2001)","DOI":"10.1145\/371920.372071"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Sun, L., Franklin, M.J., Krishnan, S., Xin, R.S.: Fine-grained partitioning for aggressive data skipping. In: Proceedings of the ACM SIGMOD International Conference on Management of data, pp. 1115\u20131126. ACM (2014)","DOI":"10.1145\/2588555.2610515"},{"key":"8_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/978-3-642-25330-0_18","volume-title":"Advances in Soft Computing","author":"SE Garza Villarreal","year":"2011","unstructured":"Garza Villarreal, S.E., Brena, R.F.: Topic mining based on graph local clustering. In: Batyrshin, I., Sidorov, G. (eds.) MICAI 2011, Part II. LNCS, vol. 7095, pp. 201\u2013212. Springer, Heidelberg (2011)"},{"key":"8_CR22","volume-title":"Text Mining: Predictive Methods for Analyzing Unstructured Information","author":"SM Weiss","year":"2010","unstructured":"Weiss, S.M., Indurkhya, N., Zhang, T., Damerau, F.: Text Mining: Predictive Methods for Analyzing Unstructured Information. Springer Science & Business Media, New York (2010)"},{"key":"8_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/978-3-319-21042-1_36","volume-title":"Web-Age Information Management","author":"Q Yang","year":"2015","unstructured":"Yang, Q., Li, Z., Jiang, J., Zhao, P., Liu, G., Liu, A., Zhu, J.: NokeaRM: employing non-key attributes in record matching. In: Dong, X.L., Yu, X., Li, J., Sun, Y. (eds.) Web-Age Information Management. LNCS, vol. 9098, pp. 438\u2013442. Springer, Heidelberg (2015)"},{"key":"8_CR24","unstructured":"Zhang, X., LeCun, Y.: Text understanding from scratch. arXiv preprint arXiv:1502.01710 (2015)"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-32025-0_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T23:20:13Z","timestamp":1748820013000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-32025-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319320243","9783319320250"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-32025-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}