{"id":"https://openalex.org/W2152056009","doi":"https://doi.org/10.1145/1526709.1526868","title":"News article extraction with template-independent wrapper","display_name":"News article extraction with template-independent wrapper","publication_year":2009,"publication_date":"2009-04-20","ids":{"openalex":"https://openalex.org/W2152056009","doi":"https://doi.org/10.1145/1526709.1526868","mag":"2152056009"},"language":"en","primary_location":{"id":"doi:10.1145/1526709.1526868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100377341","display_name":"Junfeng Wang","orcid":"https://orcid.org/0000-0003-1699-2270"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102013345","display_name":"Xiaofei He","orcid":"https://orcid.org/0009-0001-9107-2354"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei He","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428569","display_name":"Can Wang","orcid":"https://orcid.org/0000-0002-2259-1038"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062247330","display_name":"Jian Pei","orcid":"https://orcid.org/0000-0002-2200-8711"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jian Pei","raw_affiliation_strings":["Simon Fraser University, Central City, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Central City, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052757755","display_name":"Jiajun Bu","orcid":"https://orcid.org/0000-0002-1097-2044"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Bu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373367","display_name":"Chun Chen","orcid":"https://orcid.org/0000-0002-6198-7481"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Chen","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065194313","display_name":"Ziyu Guan","orcid":"https://orcid.org/0000-0003-2413-4698"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Guan","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057444662","display_name":"Gang L\u00fc","orcid":"https://orcid.org/0000-0001-5921-1839"},"institutions":[{"id":"https://openalex.org/I90727586","display_name":"Zhejiang University of Finance and Economics","ror":"https://ror.org/055vj5234","country_code":"CN","type":"education","lineage":["https://openalex.org/I90727586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Lu","raw_affiliation_strings":["College of Information, Zhejiang University of Finance and Ecomonics, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information, Zhejiang University of Finance and Ecomonics, Hangzhou, China","institution_ids":["https://openalex.org/I90727586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1085","last_page":"1086"},"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":0.9889000058174133,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9868999719619751,"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/template","display_name":"Template","score":0.7988232374191284},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7897429466247559},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6305207014083862},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4210979640483856},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3366067707538605},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06282323598861694}],"concepts":[{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.7988232374191284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897429466247559},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6305207014083862},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4210979640483856},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3366067707538605},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06282323598861694}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1526709.1526868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.167.3564","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.167.3564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.cs.uchicago.edu/%7Exiaofei/WWW2009-Wang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1551178608","https://openalex.org/W2129595335"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2121300814","https://openalex.org/W4231091074","https://openalex.org/W1886613375","https://openalex.org/W4236081792","https://openalex.org/W4250583430","https://openalex.org/W4234406076","https://openalex.org/W2010731026","https://openalex.org/W4311328601"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,36,65,68,114,118],"problem":[3,82],"of":[4,54,59,67,93,134],"template-independent":[5,86,124],"news":[6,10,76,95,105,115,119,128,148,156,160],"extraction.":[7],"The":[8],"state-of-the-art":[9],"extraction":[11,77],"method":[12],"is":[13,46,140],"based":[14],"on":[15],"template-level":[16],"wrapper":[17,37,87,125,139],"induction,":[18],"which":[19],"has":[20,41],"two":[21],"serious":[22],"limitations.":[23],"1)":[24],"It":[25,45,150],"cannot":[26],"correctly":[27],"extract":[28,127],"pages":[29,96,129,144,157],"belonging":[30],"to":[31,48,64,104],"an":[32],"unseen":[33],"template":[34,40,61],"until":[35],"for":[38,52],"that":[39],"been":[42],"generated.":[43],"2)":[44],"costly":[47],"maintain":[49],"up-to-date":[50],"wrappers":[51],"hundreds":[53],"websites,":[55],"because":[56],"any":[57],"change":[58],"a":[60,79,85,89,98,138,146],"may":[62],"lead":[63],"invalidation":[66],"corresponding":[69],"wrapper.":[70],"In":[71,136],"this":[72],"paper":[73],"we":[74],"formalize":[75],"as":[78],"machine":[80],"learning":[81],"and":[83,107,117],"learn":[84],"using":[88],"very":[90],"small":[91],"number":[92],"labeled":[94],"from":[97,130,142,145,158],"single":[99,147],"site.":[100,149],"Novel":[101],"features":[102],"dedicated":[103],"titles":[106],"bodies":[108],"are":[109,121],"developed":[110],"respectively.":[111],"Correlations":[112],"between":[113],"title":[116],"body":[120],"exploited.":[122],"Our":[123],"can":[126],"different":[131],"sites":[132],"regardless":[133],"templates.":[135],"experiments,":[137],"learned":[141],"40":[143],"achieved":[151],"98.1%":[152],"accuracy":[153],"over":[154],"3,973":[155],"12":[159],"sites.":[161]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}