{"id":"https://openalex.org/W2162955638","doi":"https://doi.org/10.1109/icpr.2008.4761539","title":"Combining content and structure similarity for XML document classification using composite SVM kernels","display_name":"Combining content and structure similarity for XML document classification using composite SVM kernels","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2162955638","doi":"https://doi.org/10.1109/icpr.2008.4761539","mag":"2162955638"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2008.4761539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2008.4761539","pdf_url":null,"source":{"id":"https://openalex.org/S4393916651","display_name":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","issn_l":"1041-3278","issn":["1041-3278","1051-4651"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 19th International Conference on Pattern Recognition","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073748464","display_name":"Saptarshi Ghosh","orcid":"https://orcid.org/0000-0002-2306-300X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Saptarshi Ghosh","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028145118","display_name":"Pabitra Mitra","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pabitra Mitra","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073748464"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.31228374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"25","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9386000037193298,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7708583474159241},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6092079281806946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.558016300201416},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5532130002975464},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4988899230957031},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45911118388175964},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4556352198123932},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4551740288734436},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.44872891902923584},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34457290172576904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15360647439956665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708583474159241},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6092079281806946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.558016300201416},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5532130002975464},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4988899230957031},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45911118388175964},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4556352198123932},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4551740288734436},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.44872891902923584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34457290172576904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15360647439956665},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icpr.2008.4761539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2008.4761539","pdf_url":null,"source":{"id":"https://openalex.org/S4393916651","display_name":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","issn_l":"1041-3278","issn":["1041-3278","1051-4651"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 19th International Conference on Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.3720","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.3720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://figment.cse.usf.edu/~sfefilat/data/papers/TuBCT10.2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.372.3614","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.372.3614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.facweb.iitkgp.ernet.in/~pabitra/paper/icpr08_xml.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W135761774","https://openalex.org/W1486401986","https://openalex.org/W1494147055","https://openalex.org/W1496255376","https://openalex.org/W1557757161","https://openalex.org/W2070046067","https://openalex.org/W2111110587","https://openalex.org/W2149684865","https://openalex.org/W2164539421","https://openalex.org/W2626905489","https://openalex.org/W6605505115","https://openalex.org/W6629057494","https://openalex.org/W6629518311","https://openalex.org/W6682304300"],"related_works":["https://openalex.org/W126212742","https://openalex.org/W4248119222","https://openalex.org/W2111998194","https://openalex.org/W2053824000","https://openalex.org/W3138464402","https://openalex.org/W4390349266","https://openalex.org/W4316658050","https://openalex.org/W2751698296","https://openalex.org/W3185823052","https://openalex.org/W2360571912"],"abstract_inverted_index":{"Combination":[0],"of":[1,13,23,37],"structure":[2,26],"and":[3,11,25,39,49,93],"content":[4,24],"features":[5],"is":[6],"necessary":[7],"for":[8,21,64],"effective":[9],"retrieval":[10],"classification":[12,55],"XML":[14,77],"documents.":[15],"Composite":[16],"kernels":[17,42],"provide":[18,52],"a":[19,34,53,60],"way":[20],"fusion":[22],"information.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"demonstrate":[32,79],"that":[33,80],"linear":[35],"combination":[36,68],"simple":[38],"low":[40],"cost":[41],"such":[43],"as":[44,89],"cosine":[45],"similarity":[46],"on":[47,73],"terms":[48],"selective":[50],"paths":[51],"good":[54],"performance.":[56],"We":[57],"also":[58],"propose":[59],"corpus-driven":[61],"entropy-based":[62],"heuristic":[63],"determining":[65],"the":[66,74,81],"optimal":[67],"weights.":[69],"Classification":[70],"experiments":[71],"performed":[72],"INEX":[75],"1.3":[76],"corpus,":[78],"composite":[82],"kernel":[83],"classifier":[84],"achieves":[85],"significantly":[86],"better":[87],"performance":[88],"compared":[90],"to":[91],"complex":[92],"time":[94],"consuming":[95],"approaches.":[96]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}