{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:50:37Z","timestamp":1760597437485},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642142451"},{"type":"electronic","value":"9783642142468"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-14246-8_19","type":"book-chapter","created":{"date-parts":[[2010,7,6]],"date-time":"2010-07-06T14:09:26Z","timestamp":1278425366000},"page":"169-181","source":"Crossref","is-referenced-by-count":16,"title":["XML Structural Similarity Search Using MapReduce"],"prefix":"10.1007","author":[{"given":"Peisen","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaofeng","family":"Sha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoling","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aoying","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Su","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"19_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-00672-2_1","volume-title":"Advances in Data and Web Management","author":"M.T. \u00d6zsu","year":"2009","unstructured":"\u00d6zsu, M.T.: Distributed XML Processing. In: Li, Q., Feng, L., Pei, J., Wang, S.X., Zhou, X., Zhu, Q.-M. (eds.) APWeb\/WAIM 2009. LNCS, vol.\u00a05446, p. 1. Springer, Heidelberg (2009)"},{"issue":"5","key":"19_CR2","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1007\/s00778-007-0049-y","volume":"17","author":"S. Abiteboul","year":"2008","unstructured":"Abiteboul, S., Benjelloun, O., Milo, T.: The Active XML project: an overview. The VLDB Journal\u00a017(5), 1019\u20131040 (2008)","journal-title":"The VLDB Journal"},{"key":"19_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/3-540-58094-8_7","volume-title":"Combinatorial Pattern Matching","author":"T. Jiang","year":"1994","unstructured":"Jiang, T., Wang, L., Zhang, K.: Alignment of Trees-An Alternative to Tree Edit. In: Crochemore, M., Gusfield, D. (eds.) CPM 1994. LNCS, vol.\u00a0807, pp. 75\u201386. Springer, Heidelberg (1994)"},{"key":"19_CR4","unstructured":"Augsten, N., B\u00f6hlen, M., Gamper, J.: Approximate matching of hierarchical data using pq-grams. In: VLDB, pp. 301\u2013312 (2005)"},{"key":"19_CR5","unstructured":"Yuan, P., Wang, X., Sha, C., Gao, M., Zhou, A.: Grams3: An efficient framework for xml structural similarity search. In: DASFAA workshop: UDM (to appear, 2010)"},{"key":"19_CR6","unstructured":"Apache\u00a0Hadoop Project (2009), http:\/\/hadoop.apache.org\/"},{"key":"19_CR7","unstructured":"Dean, J., Ghemawat, S.: MapReduce: Simplified Data Processing on Large Clusters. In: OSDI, pp. 1\u201313 (2004)"},{"key":"19_CR8","unstructured":"Broder, A.Z.: On the resemblance and containment of documents. In: Proceedings of Compression and Complexity of Sequences 1997, pp. 21\u201329 (1997)"},{"key":"19_CR9","first-page":"549","volume-title":"ICVR","author":"O. Chum","year":"2007","unstructured":"Chum, O., Philbin, J., Isard, M., Zisserman, A.: Scalable near identical image and shot detection. In: ICVR, pp. 549\u2013556. ACM, New York (2007)"},{"issue":"3","key":"19_CR10","first-page":"630","volume":"60","author":"A.Z. Broder","year":"2000","unstructured":"Broder, A.Z., Charikar, M., Frieze, A.M., Mitzenmacher, M.: Min-wise independent permutations. JCSS\u00a060(3), 630\u2013659 (2000)","journal-title":"JCSS"},{"key":"19_CR11","first-page":"604","volume-title":"ASTC","author":"P. Indyk","year":"1998","unstructured":"Indyk, P., Motwani, R.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: ASTC, pp. 604\u2013613. ACM, New York (1998)"},{"key":"19_CR12","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1145\/509907.509965","volume-title":"STOC","author":"M.S. Charikar","year":"2002","unstructured":"Charikar, M.S.: Similarity estimation techniques from rounding algorithms. In: STOC, pp. 380\u2013388. ACM, New York (2002)"},{"key":"19_CR13","unstructured":"XML\u00a0Data Repository (2009), http:\/\/www.cs.washington.edu\/research\/xmldatasets\/"},{"key":"19_CR14","unstructured":"Sigmod Record (2009), http:\/\/www.sigmod.org\/publications\/sigmod-record\/xml-edition"},{"key":"19_CR15","unstructured":"XML Twig (2009), http:\/\/xmltwig.com\/xmltwig\/"},{"key":"19_CR16","first-page":"577","volume-title":"SIGKDD","author":"S. Joshi","year":"2003","unstructured":"Joshi, S., Agrawal, N., Krishnapuram, R., Negi, S.: A bag of paths model for measuring structural similarity in Web documents. In: SIGKDD, pp. 577\u2013582. ACM, New York (2003)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Yang, R., Kalnis, P., Tung, A.K.H.: Similarity evaluation on tree-structured data. In: SIGMOD, pp. 754\u2013765 (2005)","DOI":"10.1145\/1066157.1066243"},{"issue":"5","key":"19_CR18","first-page":"43","volume":"37","author":"S. Ghemawat","year":"2003","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.T.: The Google file system. SIGOPS\u00a037(5), 43 (2003)","journal-title":"SIGOPS"},{"key":"19_CR19","first-page":"59","volume-title":"SIGOPS\/EuroSys","author":"M. Isard","year":"2007","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: Distributed data-parallel programs from sequential building blocks. In: SIGOPS\/EuroSys, pp. 59\u201372. ACM, New York (2007)"},{"key":"19_CR20","unstructured":"Hbase Project (2009), http:\/\/hadoop.apache.org\/hbase\/"},{"key":"19_CR21","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1145\/1242572.1242610","volume-title":"WWW","author":"A.S. Das","year":"2007","unstructured":"Das, A.S., Datar, M., Garg, A., Rajaram, S.: Google news personalization: scalable online collaborative filtering. In: WWW, pp. 271\u2013280. ACM, New York (2007)"},{"key":"19_CR22","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1145\/1242572.1242592","volume-title":"WWW","author":"G.S. Manku","year":"2007","unstructured":"Manku, G.S., Jain, A., Das Sarma, A.: Detecting near-duplicates for web crawling. In: WWW, pp. 141\u2013150. ACM, New York (2007)"}],"container-title":["Lecture Notes in Computer Science","Web-Age Information Management"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-14246-8_19.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T23:03:47Z","timestamp":1685660627000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-14246-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642142451","9783642142468"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-14246-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}