{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:16:55Z","timestamp":1761581815351,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030161415"},{"type":"electronic","value":"9783030161422"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-16142-2_19","type":"book-chapter","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T02:50:37Z","timestamp":1554346237000},"page":"237-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Mining Cluster Patterns in XML Corpora via Latent Topic Models of Content and Structure"],"prefix":"10.1007","author":[{"given":"Gianni","family":"Costa","sequence":"first","affiliation":[]},{"given":"Riccardo","family":"Ortale","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,3,20]]},"reference":[{"key":"19_CR1","volume-title":"Data on the Web: From Relations to Semistructured Data and XML","author":"S Abiteboul","year":"2000","unstructured":"Abiteboul, S., Buneman, P., Suciu, D.: Data on the Web: From Relations to Semistructured Data and XML. Morgan Kaufmann, Burlington (2000)"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C., Ta, N., Wang, J., Feng, J., Zaki, M.: XProj: a framework for projected structural clustering of XML documents. In: Proceedings of ACM KDD, pp. 46\u201355 (2007)","DOI":"10.1145\/1281192.1281201"},{"issue":"1\u20132","key":"19_CR3","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1020281327116","volume":"50","author":"C Andrieu","year":"2003","unstructured":"Andrieu, C., De Freitas, N., Doucet, A., Jordan, M.I.: An introduction to MCMC for machine learning. Mach. Learn. 50(1\u20132), 5\u201343 (2003)","journal-title":"Mach. Learn."},{"key":"19_CR4","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio, Y., Ducharme, R., Vincent, P., Janvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137\u20131155 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"19_CR5","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)"},{"key":"19_CR6","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."},{"issue":"3","key":"19_CR7","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1016\/j.ipm.2005.06.003","volume":"42","author":"A Bratko","year":"2006","unstructured":"Bratko, A., Filipic\u0306, B.: Exploiting structural information for semi-structured document categorization. Inf. Process. Manag. 42(3), 679\u2013694 (2006)","journal-title":"Inf. Process. Manag."},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Costa, G., Ortale, R.: Developments in partitioning XML documents by content and structure based on combining multiple clusterings. In: Proceedings of IEEE ICTAI, pp. 477\u2013482 (2013)","DOI":"10.1109\/ICTAI.2013.77"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Costa, G., Ortale, R.: A latent semantic approach to XML clustering by content and structure based on non-negative matrix factorization. In: Proceedings of IEEE ICMLA, pp. 179\u2013184 (2013)","DOI":"10.1109\/ICMLA.2013.38"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Costa, G., Ortale, R.: Mining clusters in XML corpora based on Bayesian generative topic modeling. In: Proceedings of IEEE ICMLA, pp. 515\u2013520 (2015)","DOI":"10.1109\/ICMLA.2015.148"},{"issue":"1","key":"19_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1142\/S0218213017600028","volume":"26","author":"G Costa","year":"2017","unstructured":"Costa, G., Ortale, R.: XML clustering by structure-constrained phrases: a fully-automatic approach using contextualized N-grams. Int. J. Artif. Intell. Tools 26(1), 1\u201324 (2017)","journal-title":"Int. J. Artif. Intell. Tools"},{"issue":"1","key":"19_CR12","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/s10791-017-9314-x","volume":"21","author":"G Costa","year":"2018","unstructured":"Costa, G., Ortale, R.: Machine learning techniques for XML (co-)clustering by structure-constrained phrases. Inf. Retr. J. 21(1), 24\u201355 (2018)","journal-title":"Inf. Retr. J."},{"issue":"1","key":"19_CR13","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1145\/1394251.1394255","volume":"42","author":"L Denoyer","year":"2008","unstructured":"Denoyer, L., Gallinari, P.: Report on the XML mining track at INEX 2007. ACM SIGIR Forum 42(1), 22\u201328 (2008)","journal-title":"ACM SIGIR Forum"},{"issue":"7","key":"19_CR14","doi-asserted-by":"publisher","first-page":"1858","DOI":"10.1109\/TIT.2003.813506","volume":"49","author":"DM Endres","year":"2003","unstructured":"Endres, D.M., Schindelin, J.E.: A new metric for probability distributions. IEEE Trans. Inf. Theory 49(7), 1858\u20131860 (2003)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"19_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-540-85902-4_19","volume-title":"Focused Access to XML Documents","author":"M Hagenbuchner","year":"2008","unstructured":"Hagenbuchner, M., Tsoi, A.C., Sperduti, A., Kc, M.: Efficient clustering of structured documents using graph self-organizing maps. In: Fuhr, N., Kamps, J., Lalmas, M., Trotman, A. (eds.) INEX 2007. LNCS, vol. 4862, pp. 207\u2013221. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-85902-4_19"},{"key":"19_CR16","volume-title":"Data Mining: Concepts and Techniques","author":"J Han","year":"2011","unstructured":"Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques, 3rd edn. Morgan Kaufmann, Burlington (2011)","edition":"3"},{"key":"19_CR17","unstructured":"Heinrich, G.: Parameter estimation for text analysis. Technical report, University of Leipzig (2008). http:\/\/www.arbylon.net\/publications\/text-est.pdf"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Kutty, S., Nayak, R., Li, Y.: HCX: an efficient hybrid clustering approach for XML documents. In: Proceedings of ACM DocEng, pp. 94\u201397 (2009)","DOI":"10.1145\/1600193.1600213"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Kutty, S., Nayak, R., Li, Y.: XCFS: an XML documents clustering approach using both the structure and the content. In: Proceedings of ACM CIKM, pp. 1729\u20131732 (2009)","DOI":"10.1145\/1645953.1646216"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Li, S., Huang, G., Tan, R., Pan, R.: Tag-weighted dirichlet allocation. In: Proceedings of IEEE ICDM, pp. 438\u2013447 (2013)","DOI":"10.1109\/ICDM.2013.11"},{"key":"19_CR21","unstructured":"Li, S., Li, J., Pan, R.: Tag-weighted topic model for mining semi-structured documents. In: Proceedings of IJCAI, pp. 2855\u20132861 (2013)"},{"key":"19_CR22","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of NIPS, pp. 3111\u20133119 (2013)"},{"key":"19_CR23","unstructured":"Mimno, D.M., McCallum, A.: Topic models conditioned on arbitrary features with dirichlet-multinomial regression. In: Proceedings of UAI, pp. 411\u2013418 (2008)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Ramage, D., Manning, C.D., Dumais, S.: Partially labeled topic models for interpretable text mining. In: Proceedings of ACM KDD, pp. 457\u2013465 (2011)","DOI":"10.1145\/2020408.2020481"},{"key":"19_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/978-3-540-85902-4_20","volume-title":"Focused Access to XML Documents","author":"T Tran","year":"2008","unstructured":"Tran, T., Nayak, R., Bruza, P.: Document clustering using incremental and pairwise approaches. In: Fuhr, N., Kamps, J., Lalmas, M., Trotman, A. (eds.) INEX 2007. LNCS, vol. 4862, pp. 222\u2013233. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-85902-4_20"},{"key":"19_CR26","unstructured":"Xie, P., Xing, E.P.: Integrating document clustering and topic modeling. In: Proceedings of UAI (2013)"},{"key":"19_CR27","unstructured":"Yao, J., Zerida, N.: Rare patterns to improve path-based clustering of Wikipedia articles. In: Pre-proceedings of INEX, pp. 224\u2013231 (2007)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Yi, J., Sundaresan, N.: A classifier for semi-structured documents. In: Proceedings of ACM KDD, pp. 340\u2013344 (2000)","DOI":"10.1145\/347090.347164"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-16142-2_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:19:33Z","timestamp":1709813973000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-16142-2_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030161415","9783030161422"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-16142-2_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"20 March 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macau","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 April 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.pakdd2019.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft Conf. Man. Toolkit CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"542","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":"137","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":"0","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":"25% - 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":"3.79","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":"5.85","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":"In addition, there were 31 PAKDD 2019 Workshops' papers accepted for publication","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)"}}]}}