{"id":"https://openalex.org/W2034416661","doi":"https://doi.org/10.1145/1458082.1458298","title":"Closing the loop in webpage understanding","display_name":"Closing the loop in webpage understanding","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2034416661","doi":"https://doi.org/10.1145/1458082.1458298","mag":"2034416661"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","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/A5108999804","display_name":"Chunyu Yang","orcid":"https://orcid.org/0000-0001-5615-2693"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050482594","display_name":"Yong Cao","orcid":"https://orcid.org/0000-0003-4555-072X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Cao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047496977","display_name":"Zaiqing Nie","orcid":"https://orcid.org/0000-0002-1134-2343"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaiqing Nie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620306","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0001-7701-234X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8757,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84055697,"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":"1397","last_page":"1398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9857000112533569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7791715860366821},{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.686377227306366},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6760985851287842},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5741317272186279},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45536819100379944},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4206928014755249},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3288871645927429},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.31529462337493896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07124361395835876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791715860366821},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.686377227306366},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6760985851287842},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5741317272186279},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45536819100379944},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4206928014755249},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3288871645927429},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31529462337493896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07124361395835876},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W65845428","https://openalex.org/W1505544955","https://openalex.org/W1513861746","https://openalex.org/W1616576116","https://openalex.org/W1973483159","https://openalex.org/W1978833300","https://openalex.org/W2045993505","https://openalex.org/W2051434435","https://openalex.org/W2096496923","https://openalex.org/W2104086170","https://openalex.org/W2115770258","https://openalex.org/W2126185232","https://openalex.org/W2128341918","https://openalex.org/W2129712609","https://openalex.org/W2130766266","https://openalex.org/W2135479443","https://openalex.org/W2143309843","https://openalex.org/W2147880316","https://openalex.org/W2148210463","https://openalex.org/W2150721933","https://openalex.org/W2152455533","https://openalex.org/W2157316480","https://openalex.org/W2158188757","https://openalex.org/W2160196229","https://openalex.org/W2166407869","https://openalex.org/W2167138081","https://openalex.org/W2167859982","https://openalex.org/W2168358004","https://openalex.org/W2341078838","https://openalex.org/W3140899690","https://openalex.org/W4233527139"],"related_works":["https://openalex.org/W2116422677","https://openalex.org/W2517007886","https://openalex.org/W2383994331","https://openalex.org/W1522019333","https://openalex.org/W278047738","https://openalex.org/W2076369646","https://openalex.org/W2373884197","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Little":[0],"work":[1],"has":[2],"been":[3],"done":[4],"towards":[5],"an":[6,43],"integrated":[7],"statistical":[8],"model":[9],"for":[10],"understanding":[11,38,41],"webpage":[12],"structures":[13],"and":[14,39],"processing":[15],"natural":[16],"language":[17],"sentences":[18],"within":[19],"the":[20,49],"HTML":[21],"elements.":[22],"This":[23],"paper":[24],"proposed":[25],"a":[26],"novel":[27],"framework":[28,51],"called":[29],"WebNLP":[30,50],"which":[31],"enables":[32],"bidirectional":[33],"integration":[34],"of":[35],"page":[36],"structure":[37],"text":[40],"in":[42],"iterative":[44],"manner.":[45],"Experiments":[46],"show":[47],"that":[48],"achieved":[52],"significantly":[53],"better":[54],"performance.":[55]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
