{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:51:41Z","timestamp":1740160301269,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2017,3,28]],"date-time":"2017-03-28T00:00:00Z","timestamp":1490659200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"The Education University of Hong Kong","award":["RG 18\/2015-2016R"],"award-info":[{"award-number":["RG 18\/2015-2016R"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s13042-017-0657-9","type":"journal-article","created":{"date-parts":[[2017,3,28]],"date-time":"2017-03-28T13:55:44Z","timestamp":1490709344000},"page":"1473-1487","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A learning framework for information block search based on probabilistic graphical models and Fisher Kernel"],"prefix":"10.1007","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4581-9912","authenticated-orcid":false,"given":"Tak-Lam","family":"Wong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wai","family":"Lam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fu Lee","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,28]]},"reference":[{"key":"657_CR1","doi-asserted-by":"publisher","unstructured":"Arun K, Govindan V (2016) A context-aware semantic modeling framework for efficient image retrieval. Int J Mach Learn Cybern.\u00a0doi: 10.1007\/s13042-016-0498-y","DOI":"10.1007\/s13042-016-0498-y"},{"key":"657_CR2","doi-asserted-by":"crossref","unstructured":"Bah A, Chandar P, Carterette B (2015) Document comprehensiveness and user preferences in novelty search tasks. In: Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval, pp 735\u2013738","DOI":"10.1145\/2766462.2767820"},{"key":"657_CR3","doi-asserted-by":"crossref","unstructured":"Bilenko M, Kamath B, Mooney R (2006) Adaptive blocking: learning to scale up record linkage. In: Proceedings of the sixth IEEE international conference on data mining (ICDM), pp 87\u201396","DOI":"10.1109\/ICDM.2006.13"},{"key":"657_CR4","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"key":"657_CR5","doi-asserted-by":"crossref","unstructured":"Cai Y, Li Q (2010) Personalized search by tag-based user profile and resource profile in collaborative tagging systems. In: Proceedings of the 19th ACM international conference on information and knowledge management, pp 969\u2013978","DOI":"10.1145\/1871437.1871561"},{"key":"657_CR6","doi-asserted-by":"crossref","unstructured":"Cai D, Yu S, Wen J-R, Ma W-Y (2004) Block-based web search. In: Proceedings of the 27th annual international ACM SIGIR conference on research and development in information retrieval, pp 456\u2013463","DOI":"10.1145\/1008992.1009070"},{"issue":"3","key":"657_CR7","doi-asserted-by":"crossref","first-page":"2690","DOI":"10.1016\/j.eswa.2011.08.125","volume":"39","author":"Y Chen","year":"2012","unstructured":"Chen Y, Lee S, Huang C-R (2012) A robust web personal name information extraction system. Exp Syst Appl 39(3):2690\u20132699","journal-title":"Exp Syst Appl"},{"issue":"5","key":"657_CR8","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1145\/1017460.1017462","volume":"51","author":"V Crescenzi","year":"2004","unstructured":"Crescenzi V, Mecca G (2004) Automatic information extraction from large websites. J ACM 51(5):731\u2013779","journal-title":"J ACM"},{"key":"657_CR9","doi-asserted-by":"crossref","unstructured":"Culotta A, Wick M, Hall R, Marzilli M, McCallum A (2007) Canonicalization of database records using adaptive similarity measures. In: Proceedings of the thirteenth ACM SIGKDD international conference on knowledge discovery and data mining, pp 201\u2013209","DOI":"10.1145\/1281192.1281217"},{"issue":"4","key":"657_CR10","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/s13042-014-0275-8","volume":"7","author":"A Ekbal","year":"2014","unstructured":"Ekbal A, Saha S, Sikdar U (2014) On active annotation for named entity recognition. Int J Mach Learn Cybern 7(4):623\u2013640","journal-title":"Int J Mach Learn Cybern"},{"key":"657_CR11","doi-asserted-by":"crossref","unstructured":"Fernandes D, de\u00a0Moura ES, Ribeiro-Neto B, da\u00a0Silva AS, Gon\u00e7alves MA (2007) Computing block importance for searching on web sites. In: Proceedings of the sixteenth ACM conference on Conference on information and knowledge management(CIKM), pp 165\u2013174","DOI":"10.1145\/1321440.1321466"},{"key":"657_CR12","doi-asserted-by":"crossref","unstructured":"Hao Q, Cai R, Pang Y, Zhang L (2011) From one tree to a forest: a unified solution for structured web data extraction. In: Proceedings of the 34th international ACM SIGIR conference on research and development in information retrieval, pp 775\u2013784","DOI":"10.1145\/2009916.2010020"},{"key":"657_CR13","doi-asserted-by":"crossref","unstructured":"Hu Y, Xin G, Song R, Hu G, Shi S, Cao Y, Li H (2005) Title extraction from bodies of html documents and its application to web page retrieval. In: Proceedings of the 28th international ACM SIGIR conference on research and development in information retrieval, pp 250\u2013257","DOI":"10.1145\/1076034.1076079"},{"key":"657_CR14","unstructured":"Jaakkola T, Haussler D (1998) Exploiting generative models in discriminative classifiers. In: Advances in neural information processing systems 11, neural information processing systems, pp 487\u2013493"},{"key":"657_CR15","unstructured":"Jajishirzi H, Yih W, Kolcz A (2010) Adaptive near-duplicate detection via similarity learning. In: Proceedings of the 33st international ACM SIGIR conference on research and development in information retrieval, pp 419\u2013426"},{"key":"657_CR16","unstructured":"Lafferty J, McCallum A, Pereira F (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of 18th international conference on machine learning, pp 282\u2013289"},{"key":"657_CR17","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.dss.2014.05.005","volume":"65","author":"RY Lau","year":"2014","unstructured":"Lau RY, Li C, Liao SS (2014) Social analytics: learning fuzzy product ontologies for aspect-oriented sentiment analysis. Decis Support Syst 65:80\u201394","journal-title":"Decis Support Syst"},{"key":"657_CR18","doi-asserted-by":"crossref","unstructured":"Lin S-H, Ho J-M (2002) Discovering informative content blocks from web documents. In: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining (SIGKDD), pp 588\u2013593","DOI":"10.1145\/775047.775134"},{"issue":"2","key":"657_CR19","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.eswa.2013.07.048","volume":"41","author":"S Lin","year":"2014","unstructured":"Lin S, Jin P, Zhao X, Yue L (2014) Exploiting temporal information in web search. Exp Syst Appl 41(2):331\u2013341","journal-title":"Exp Syst Appl"},{"issue":"3","key":"657_CR20","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TKDE.2009.109","volume":"22","author":"W Liu","year":"2010","unstructured":"Liu W, Meng X, Meng W (2010) Vide: a vision-based approach for deep web data extraction. IEEE Trans Knowl Data Eng 22(3):447\u2013460","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"657_CR21","doi-asserted-by":"crossref","unstructured":"Li X, Wang Y-Y, Acero A (2009) Extracting structured information from user queries with semi-supervised conditional random fields. In: Proceedings of the 30th international ACM SIGIR conference on research and development in information retrieval, pp 572\u2013579","DOI":"10.1145\/1571941.1572039"},{"key":"657_CR22","doi-asserted-by":"crossref","unstructured":"Luo P, Lin F, Xiong Y, Zhao Y, Shi Z (2009) Towards combining web classification and web information extraction: a case study. In: Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining, pp 1235\u20131244","DOI":"10.1145\/1557019.1557152"},{"key":"657_CR23","doi-asserted-by":"crossref","unstructured":"McCallum A, Li W (2003) Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons. In: Proceedings of the seventh conference on natural language learning, pp 188\u2013191","DOI":"10.3115\/1119176.1119206"},{"key":"657_CR24","doi-asserted-by":"crossref","unstructured":"Miao G, Tatemura J, Hsiung W-P, Sawires A, Moser LE (2009) Extracting data records from the web using tag path clustering. In: Proceedings of the eighteenth international world wide web conference (WWW), pp 81\u2013990","DOI":"10.1145\/1526709.1526841"},{"key":"657_CR25","unstructured":"Monge A, Elkan C (1997) An efficient domain-independent algorithm for detecting approximately duplicate database records. In: Research issues on data mining and knowledge discovery"},{"issue":"1","key":"657_CR26","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/s13042-011-0037-9","volume":"3","author":"Y Qin","year":"2012","unstructured":"Qin Y, Zheng D, Zhao T (2012) Research on search results optimization technology with category features integration. Int J Mach Learn Cybern 3(1):71\u201376","journal-title":"Int J Mach Learn Cybern"},{"issue":"22","key":"657_CR27","doi-asserted-by":"crossref","first-page":"8805","DOI":"10.1016\/j.eswa.2015.07.033","volume":"42","author":"JR Ruiz-Sarmiento","year":"2015","unstructured":"Ruiz-Sarmiento JR, Galindo C, Gonzalez-Jimenez J (2015) Scene object recognition for mobile robots through semantic knowledge and probabilistic graphical models. Exp Syst Appl 42(22):8805\u20138816","journal-title":"Exp Syst Appl"},{"key":"657_CR28","doi-asserted-by":"crossref","unstructured":"Sha F, Pereira F (2003) Shallow parsing with conditional random fields. In: Proceedings of the 2003 conference of the North American chapter of the association for computational linguistics on human language technology, pp 134\u2013141","DOI":"10.3115\/1073445.1073473"},{"key":"657_CR29","doi-asserted-by":"crossref","unstructured":"Song X, Liu J, Cao Y, Lin C-Y, Hon H-W (2010) Automatic extraction of web data records containing user-generated content. In: Proceedings of the nineteenth ACM conference on Conference on information and knowledge management(CIKM), pp 39\u201348","DOI":"10.1145\/1871437.1871447"},{"key":"657_CR30","doi-asserted-by":"crossref","unstructured":"Sun Q, Li R, Luo D, Wu X (2008) Text segmentation with lda-based Fisher Kernel. In: Proceedings of the 46th annual meeting of the association for computational linguistics on human language technologies: short papers, pp 269\u2013272","DOI":"10.3115\/1557690.1557768"},{"key":"657_CR31","doi-asserted-by":"crossref","unstructured":"Sun F, Song D, Liao L (2011) Dom based content extraction via text density. In: Proceedings of the 34th international ACM SIGIR conference on research and development in information retrieval, pp 245\u2013254","DOI":"10.1145\/2009916.2009952"},{"key":"657_CR32","unstructured":"Sutton C, Rohanimanesh K, McCallum A (2004) Dynamic conditional random fileds: factorized probabilistic models for labeling and segmenting sequence data. In: Proceedings of twenty-first international conference on machine learning, pp 783\u2013790"},{"key":"657_CR33","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1198\/016214506000000302","volume":"101","author":"Y Teh","year":"2006","unstructured":"Teh Y, Jordan M, Beal M, Blei D (2006) Hierarchical dirichlet processes. J Am Stat Assoc 101:1566\u20131581","journal-title":"J Am Stat Assoc"},{"key":"657_CR34","doi-asserted-by":"crossref","unstructured":"Theobald M, Siddharth J, Paepcke A (2008) Spotsigs: robust and efficient near duplicate detection in large web collections. In: Proceedings of the 31st international ACM SIGIR conference on research and development in information retrieval, pp 563\u2013370","DOI":"10.1145\/1390334.1390431"},{"key":"657_CR35","doi-asserted-by":"crossref","unstructured":"Turmo J, Ageno A, Catala N (2006) Adaptive information extraction. ACM Comput Surv 38(2). Article 4","DOI":"10.1145\/1132956.1132957"},{"key":"657_CR36","unstructured":"van\u00a0der Maaten L (2011) Learning discriminative Fisher Kernels. In: Proceedings of twenty-eighth international conference on machine learning"},{"key":"657_CR37","unstructured":"Vo D-T, Hai V, Ock C-Y (2015) Exploiting language models to classify events from twitter. Comput Intell Neurosci. Article ID 401024"},{"key":"657_CR38","doi-asserted-by":"crossref","unstructured":"Wang T, Cai Y, Leung HF, Cai Z, Min H (2015) Entropy-based term weighting schemes for text categorization in vsm. In: Proceedings of the IEEE 27th international conference on tools with artificial intelligence, pp 325\u2013332","DOI":"10.1109\/ICTAI.2015.57"},{"key":"657_CR39","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1109\/TKDE.2009.155","volume":"22","author":"C Yang","year":"2010","unstructured":"Yang C, Cao Y, Nie Z, Zhou J, Wen J-R (2010) Closing the loop in webpage understanding. IEEE Trans Knowl Data Eng 22:639\u2013650","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"657_CR40","doi-asserted-by":"crossref","unstructured":"Yan Y, Yin X-C, Li S, Yang M, Hao H-W (2015) Learning document semantic representation with hybrid deep belief network. Comput Intell Neurosci. Article ID 650527","DOI":"10.1155\/2015\/650527"},{"key":"657_CR41","doi-asserted-by":"crossref","unstructured":"Zheng S, Song R, Wen J-R, Giles CL (2009) Efficient record-level wrapper induction. In: Proceeding of the 18th ACM international conference on information and knowledge management, pp 47\u201356","DOI":"10.1145\/1645953.1645962"},{"key":"657_CR42","first-page":"1583","volume":"9","author":"J Zhu","year":"2008","unstructured":"Zhu J, Nie Z, Zhang B, Wen J-R (2008) Dynamic hierarchical markov random fields for integrated web data extraction. J Mach Learn Res 9:1583\u20131614","journal-title":"J Mach Learn Res"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13042-017-0657-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-017-0657-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-017-0657-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T04:57:46Z","timestamp":1568955466000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13042-017-0657-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,28]]},"references-count":42,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["657"],"URL":"https:\/\/doi.org\/10.1007\/s13042-017-0657-9","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2017,3,28]]}}}