{"id":"https://openalex.org/W2145108204","doi":"https://doi.org/10.1145/1242572.1242785","title":"Integrating web directories by learning their structures","display_name":"Integrating web directories by learning their structures","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2145108204","doi":"https://doi.org/10.1145/1242572.1242785","mag":"2145108204"},"language":"en","primary_location":{"id":"doi:10.1145/1242572.1242785","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","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/A5086292931","display_name":"Christopher C. Yang","orcid":"https://orcid.org/0000-0001-5463-6926"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Christopher C. Yang","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055824102","display_name":"Jianfeng Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Lin","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086292931"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.1417551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1239","last_page":"1240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9947999715805054,"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":0.7663515210151672},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7105934023857117},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6074767112731934},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5790294408798218},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5301958918571472},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4567311108112335},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.43504413962364197},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.34005576372146606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08042630553245544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663515210151672},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7105934023857117},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6074767112731934},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5790294408798218},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5301958918571472},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4567311108112335},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.43504413962364197},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.34005576372146606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08042630553245544},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1242572.1242785","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.722.1094","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.722.1094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cci.drexel.edu/faculty/cyang/papers/yang2007d.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1499976586","https://openalex.org/W1576520375","https://openalex.org/W1590030008","https://openalex.org/W1604938182","https://openalex.org/W2008896880","https://openalex.org/W2027780767","https://openalex.org/W2062847911"],"related_works":["https://openalex.org/W2037906003","https://openalex.org/W4378699829","https://openalex.org/W2953265498","https://openalex.org/W2533455610","https://openalex.org/W2083329789","https://openalex.org/W1892772476","https://openalex.org/W2376574812","https://openalex.org/W2074888472","https://openalex.org/W2160189941","https://openalex.org/W2182622516"],"abstract_inverted_index":{"Documents":[0],"in":[1,107],"the":[2,51,103,109,119],"Web":[3,29,115],"are":[4,25,47,100],"often":[5],"organized":[6],"using":[7],"category":[8,23,32,62,76,97],"trees":[9,24,63],"by":[10,91],"information":[11,80,94],"providers":[12,39],"(e.g.":[13,19],"CNN,":[14],"BBC)":[15],"or":[16],"search":[17],"engines":[18],"Google,":[20],"Yahoo!).":[21],"Such":[22],"commonly":[26],"known":[27],"as":[28],"directories.":[30],"The":[31],"tree":[33,77],"structures":[34],"from":[35,81],"different":[36],"internet":[37],"content":[38],"may":[40],"be":[41],"similar":[42],"to":[43,59,71,78],"some":[44],"extent":[45],"but":[46],"usually":[48],"not":[49],"exactly":[50],"same.":[52],"As":[53],"a":[54,74],"result,":[55],"it":[56],"is":[57,122],"desirable":[58],"integrate":[60],"these":[61],"together":[64],"so":[65],"that":[66,118],"web":[67],"users":[68],"only":[69],"need":[70],"browse":[72],"through":[73],"unified":[75],"extract":[79],"multiple":[82,96],"providers.":[83],"In":[84],"this":[85,89],"paper,":[86],"we":[87],"address":[88],"problem":[90],"capturing":[92],"structural":[93],"of":[95,105],"trees,":[98],"which":[99],"embedded":[101],"with":[102,113],"knowledge":[104],"professional":[106],"organizing":[108],"documents.":[110],"Our":[111],"experiments":[112],"real":[114],"data":[116],"show":[117],"proposed":[120],"technique":[121],"promising.":[123]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
