{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T23:19:40Z","timestamp":1725751180860},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642411533"},{"type":"electronic","value":"9783642411540"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-41154-0_15","type":"book-chapter","created":{"date-parts":[[2013,10,7]],"date-time":"2013-10-07T03:48:42Z","timestamp":1381117722000},"page":"202-215","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting Structural Similarity for Automatic Information Extraction from Lists"],"prefix":"10.1007","author":[{"given":"Dat T.","family":"Huynh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shazia","family":"Sadiq","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"15_CR1","unstructured":"Rise - a repository of online information sources used in information extraction tasks (1998), http:\/\/www.isi.edu\/info-agents\/rise\/index.html"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Agichtein, E., Ganti, V.: Mining reference tables for automatic text segmentation. In: Proceedings of the Tenth ACM SIGKDD Conference, pp. 20\u201329 (2004)","DOI":"10.1145\/1014052.1014058"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting structured data from web pages. In: Proceedings of the 2003 ACM SIGMOD, pp. 337\u2013348 (2003)","DOI":"10.1145\/872797.872799"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Borkar, V., Deshmukh, K., Sarawagi, S.: Automatic segmentation of text into structured records. In: Proceedings of ACM SIGMOD, pp. 175\u2013186 (2001)","DOI":"10.1145\/376284.375682"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Cortez, E., da Silva, A.S., Gon\u00e7alves, M.A., de Moura, E.S.: Ondux: on-demand unsupervised learning for information extraction. In: Proceedings of the 2010 ACM SIGMOD, pp. 807\u2013818 (2010)","DOI":"10.1145\/1807167.1807254"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: Roadrunner: Towards automatic data extraction from large web sites. In: Proceedings of the 27th International Conference on Very Large Data bases, pp. 109\u2013118 (2001)","DOI":"10.1145\/564691.564778"},{"key":"15_CR7","first-page":"1","volume":"19","author":"A.K. Elmagarmid","year":"2007","unstructured":"Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: A survey. IEEE TKDE\u00a019, 1\u201316 (2007)","journal-title":"IEEE TKDE"},{"key":"15_CR8","unstructured":"Freitag, D., McCallum, A.: Information extraction with hmm structures learned by stochastic optimization. In: Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence, pp. 584\u2013589. AAAI Press (2000)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Gravano, L., Ipeirotis, P.G., Koudas, N., Srivastava, D.: Text joins in an rdbms for web data integration. In: Proceedings of the 12th International Conference on World Wide Web, pp. 90\u2013101. ACM (2003)","DOI":"10.1145\/775165.775166"},{"key":"15_CR10","unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning, pp. 282\u2013289 (2001)"},{"issue":"8","key":"15_CR11","first-page":"707","volume":"10","author":"V. Levenshtein","year":"1966","unstructured":"Levenshtein, V.: Binary codes capable of correcting deletions, insertions, and reversals. Soviet Physics Doklady\u00a010(8), 707\u2013710 (1966)","journal-title":"Soviet Physics Doklady"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Mansuri, I.R., Sarawagi, S.: Integrating unstructured data into relational databases. In: Proceedings of the 22nd ICDE, pp. 29\u201340 (2006)","DOI":"10.1109\/ICDE.2006.83"},{"key":"15_CR13","volume-title":"Probabilistic reasoning in intelligent systems: networks of plausible inference","author":"J. Pearl","year":"1988","unstructured":"Pearl, J.: Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)"},{"key":"15_CR14","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1016\/j.ipm.2005.09.002","volume":"42","author":"F. Peng","year":"2006","unstructured":"Peng, F., McCallum, A.: Information extraction from research papers using crfs. Information Processing and Management\u00a042, 963\u2013979 (2006)","journal-title":"Information Processing and Management"},{"key":"15_CR15","volume-title":"Introduction to Modern Information Retrieval","author":"G. Salton","year":"1986","unstructured":"Salton, G., McGill, M.J.: Introduction to Modern Information Retrieval. McGraw-Hill, Inc., New York (1986)"},{"issue":"3","key":"15_CR16","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1561\/1900000003","volume":"1","author":"S. Sarawagi","year":"2008","unstructured":"Sarawagi, S.: Information extraction. Foundation and Trends in Databases\u00a01(3), 261\u2013377 (2008)","journal-title":"Foundation and Trends in Databases"},{"key":"15_CR17","unstructured":"Seymore, K., Mccallum, A., Rosenfeld, R.: Learning hidden markov model structure for information extraction. In: AAAI 1999 Workshop on Machine Learning for Information Extraction, pp. 37\u201342 (1999)"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, C., Mahmud, J., Ramakrishnan, I.V.: Exploiting structured reference data for unsupervised text segmentation with conditional random fields. In: Proceedings of the SIAM International Conference on Data Mining, pp. 420\u2013431 (2008)","DOI":"10.1137\/1.9781611972788.38"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems Engineering \u2013 WISE 2013"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-41154-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T23:45:42Z","timestamp":1688514342000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-41154-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642411533","9783642411540"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-41154-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}