{"id":"https://openalex.org/W2201534957","doi":"https://doi.org/10.1145/2736277.2741659","title":"Automatic Web Content Extraction by Combination of Learning and Grouping","display_name":"Automatic Web Content Extraction by Combination of Learning and Grouping","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W2201534957","doi":"https://doi.org/10.1145/2736277.2741659","mag":"2201534957"},"language":"en","primary_location":{"id":"doi:10.1145/2736277.2741659","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th 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/A5068376142","display_name":"Shanchan Wu","orcid":"https://orcid.org/0000-0001-6033-5353"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shanchan Wu","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107840655","display_name":"Jerry Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerry Liu","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077871435","display_name":"Jian Fan","orcid":"https://orcid.org/0000-0001-5009-9588"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Fan","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068376142"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":13.1754,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.98509345,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1264","last_page":"1274"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9686999917030334,"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/T11478","display_name":"Caching and Content Delivery","score":0.9685999751091003,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8420412540435791},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7532657384872437},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5600529313087463},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.5203813314437866},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5120261311531067},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5091609358787537},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.49604853987693787},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48077982664108276},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4683598577976227},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4504736363887787},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4274293780326843},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4220074713230133},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42060935497283936},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4170593321323395},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.415620893239975},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.360140860080719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32952404022216797},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09447121620178223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420412540435791},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7532657384872437},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5600529313087463},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.5203813314437866},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5120261311531067},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5091609358787537},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.49604853987693787},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48077982664108276},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4683598577976227},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4504736363887787},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4274293780326843},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4220074713230133},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42060935497283936},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4170593321323395},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.415620893239975},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.360140860080719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32952404022216797},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09447121620178223},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2736277.2741659","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.695.4523","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.695.4523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2015.it/documents/proceedings/proceedings/p1264.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1566513354","https://openalex.org/W1965698293","https://openalex.org/W1966102147","https://openalex.org/W1989338554","https://openalex.org/W1991565788","https://openalex.org/W2003204742","https://openalex.org/W2019264297","https://openalex.org/W2019577381","https://openalex.org/W2040075907","https://openalex.org/W2051141368","https://openalex.org/W2076665947","https://openalex.org/W2084358158","https://openalex.org/W2086017131","https://openalex.org/W2090193136","https://openalex.org/W2119966992","https://openalex.org/W2120101509","https://openalex.org/W2129595335","https://openalex.org/W2140208587","https://openalex.org/W2145076056","https://openalex.org/W2158051716","https://openalex.org/W2167859982"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2998827288","https://openalex.org/W2083329789","https://openalex.org/W2897171874","https://openalex.org/W4255475599","https://openalex.org/W2278505189","https://openalex.org/W1987716395"],"abstract_inverted_index":{"Web":[0,83],"pages":[1],"consist":[2],"of":[3,32,38,73,82],"not":[4,26],"only":[5,78],"actual":[6,39,100,144],"content,":[7,40],"but":[8],"also":[9],"other":[10],"elements":[11],"such":[12,48],"as":[13,49,104],"branding":[14],"banners,":[15],"navigational":[16],"elements,":[17],"advertisements,":[18],"copyright":[19],"etc.":[20],"This":[21],"noisy":[22,163],"content":[23,101,145],"is":[24,146],"typically":[25],"related":[27],"to":[28,68,90,122,159],"the":[29,33,36,99,117,135,140,143,170],"main":[30],"subjects":[31],"webpages.":[34],"Identifying":[35],"part":[37],"or":[41,88],"clipping":[42],"web":[43,52],"pages,":[44,84,87],"has":[45,89,185],"many":[46,64],"applications,":[47],"high":[50,186],"quality":[51,187],"printing,":[53],"e-reading":[54],"on":[55,79,134,139,177],"mobile":[56],"devices":[57],"and":[58,165,181,189],"data":[59,164,168],"mining.":[60],"Although":[61],"there":[62],"are":[63,131],"existing":[65],"methods":[66],"attempting":[67],"address":[69],"this":[70],"task,":[71],"most":[72],"them":[74],"can":[75],"either":[76],"work":[77],"certain":[80],"types":[81],"e.g.":[85],"article":[86],"develop":[91,112,155],"different":[92,95],"models":[93],"for":[94,169],"websites.":[96],"We":[97,111,173],"formulate":[98],"identifying":[102],"problem":[103],"a":[105,124,150,156,178],"DOM":[106,118],"tree":[107,119],"node":[108,120],"selection":[109],"problem.":[110],"multiple":[113],"features":[114],"by":[115],"utilizing":[116],"properties":[121],"train":[123],"machine":[125],"learning":[126,136],"model.":[127,137],"Then":[128],"candidate":[129,171],"nodes":[130],"selected":[132],"based":[133],"Based":[138],"observation":[141],"that":[142],"usually":[147],"located":[148],"in":[149],"spatially":[151],"continuous":[152],"block,":[153],"we":[154],"grouping":[157],"technology":[158],"further":[160],"filter":[161],"out":[162],"pick":[166],"missing":[167],"nodes.":[172],"conduct":[174],"extensive":[175],"experiments":[176],"real":[179],"dataset":[180],"demonstrate":[182],"our":[183],"solution":[184],"outputs":[188],"outperforms":[190],"several":[191],"baseline":[192],"methods.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}