{"id":"https://openalex.org/W2051141368","doi":"https://doi.org/10.1145/1557019.1557163","title":"Can we learn a template-independent wrapper for news article extraction from a single training site?","display_name":"Can we learn a template-independent wrapper for news article extraction from a single training site?","publication_year":2009,"publication_date":"2009-06-28","ids":{"openalex":"https://openalex.org/W2051141368","doi":"https://doi.org/10.1145/1557019.1557163","mag":"2051141368"},"language":"en","primary_location":{"id":"doi:10.1145/1557019.1557163","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5025362382","display_name":"Junfeng Wang","orcid":"https://orcid.org/0000-0002-5720-056X"},"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":true,"raw_author_name":"Junfeng Wang","raw_affiliation_strings":["Zhejiang Key Lab. of Service Robot, College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab. of Service Robot, College of Computer Science, 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 Key Lab. of Service Robot, College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab. of Service Robot, College of Computer Science, 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 Key Lab. of Service Robot, College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab. of Service Robot, College of Computer Science, 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":["School of Computer Science, Simon Fraser University, Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Simon Fraser University, Vancouver, 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 Key Lab. of Service Robot, College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab. of Service Robot, College of Computer Science, 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 Key Lab. of Service Robot, College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Key Lab. of Service Robot, College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000129168","display_name":"Wei Vivian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Vivian Zhang","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5025362382"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":14.7497,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.98697543,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1345","last_page":"1354"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9801999926567078,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7997521162033081},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6938409805297852},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6816796064376831},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5399839878082275},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.5252178311347961},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4541669487953186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997521162033081},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6938409805297852},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6816796064376831},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5399839878082275},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.5252178311347961},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4541669487953186},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1557019.1557163","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.3552","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.3552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.sfu.ca/%7Ejpei/publications/NewsExtraction-KDD09.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":27,"referenced_works":["https://openalex.org/W126744842","https://openalex.org/W1549656520","https://openalex.org/W1551178608","https://openalex.org/W1567298333","https://openalex.org/W1618905105","https://openalex.org/W1997162771","https://openalex.org/W1997208625","https://openalex.org/W2005646337","https://openalex.org/W2012575882","https://openalex.org/W2048001624","https://openalex.org/W2065568440","https://openalex.org/W2102694093","https://openalex.org/W2104086170","https://openalex.org/W2119577990","https://openalex.org/W2128341918","https://openalex.org/W2129595335","https://openalex.org/W2132022450","https://openalex.org/W2135479443","https://openalex.org/W2143309843","https://openalex.org/W2144415203","https://openalex.org/W2145076056","https://openalex.org/W2150721933","https://openalex.org/W2153072229","https://openalex.org/W2155195660","https://openalex.org/W2167859982","https://openalex.org/W3000265418","https://openalex.org/W3015882749"],"related_works":["https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2106946048","https://openalex.org/W2120930843","https://openalex.org/W42013907","https://openalex.org/W2268257560"],"abstract_inverted_index":{"Automatic":[0],"news":[1,4,14,19,57,96,105,124,134,142,145,154,177,182,207,216,220],"extraction":[2,20,97,106],"from":[3,126,156,201,204,218],"pages":[5,38,125,155,203,217],"is":[6,46],"important":[7],"in":[8,98,185,191],"many":[9],"Web":[10,95,104],"applications":[11],"such":[12],"as":[13,107,190],"aggregation.":[15],"However,":[16],"the":[17,32,67,71,91,176,180,186,192],"existing":[18,33,72],"methods":[21,34,73],"based":[22],"on":[23,214],"template-level":[24],"wrapper":[25,116,151,199],"induction":[26],"have":[27],"three":[28],"serious":[29],"limitations.":[30],"First,":[31],"cannot":[35],"correctly":[36],"extract":[37,76,153,166],"belonging":[39],"to":[40,48,133],"an":[41,210],"unseen":[42],"template.":[43],"Second,":[44],"it":[45],"costly":[47],"maintain":[49],"up-to-date":[50],"wrappers":[51],"for":[52],"a":[53,63,99,108,114,118,127,198,205],"large":[54],"amount":[55],"of":[56,62,93,122,160,212],"websites,":[58],"because":[59],"any":[60],"change":[61],"template":[64],"may":[65],"invalidate":[66],"corresponding":[68],"wrapper.":[69],"Last,":[70],"can":[74,152,165],"merely":[75],"unformatted":[77],"plain":[78],"texts,":[79,169],"and":[80,112,136,144,173,179],"thus":[81],"are":[82,138,147,184],"not":[83,167],"user":[84],"friendly.":[85],"In":[86,195],"this":[87],"paper,":[88],"we":[89],"tackle":[90],"problem":[92,111],"template-independent":[94,115,150],"user-friendly":[100],"way.":[101],"We":[102],"formalize":[103],"machine":[109],"learning":[110],"learn":[113],"using":[117],"very":[119],"small":[120],"number":[121],"labeled":[123],"single":[128,206],"site.":[129],"Novel":[130],"features":[131],"dedicated":[132],"titles":[135,143],"bodies":[137,146,178],"developed.":[139],"Correlations":[140],"between":[141],"exploited.":[148],"Our":[149],"different":[157],"sites":[158],"regardless":[159],"templates.":[161],"Moreover,":[162],"our":[163,196],"approach":[164],"only":[168],"but":[170],"also":[171],"images":[172],"animates":[174],"within":[175],"extracted":[181],"articles":[183],"same":[187],"visual":[188],"style":[189],"original":[193],"pages.":[194],"experiments,":[197],"learned":[200],"40":[202],"site":[208],"achieved":[209],"accuracy":[211],"98.1%":[213],"3,973":[215],"12":[219],"sites.":[221]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}