{"id":"https://openalex.org/W1991565788","doi":"https://doi.org/10.1145/1600193.1600208","title":"Web article extraction for web printing","display_name":"Web article extraction for web printing","publication_year":2009,"publication_date":"2009-09-16","ids":{"openalex":"https://openalex.org/W1991565788","doi":"https://doi.org/10.1145/1600193.1600208","mag":"1991565788"},"language":"en","primary_location":{"id":"doi:10.1145/1600193.1600208","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM symposium on Document engineering","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/A5100752685","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6645-4721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["HP Labs, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","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","HP Labs, Palo ALto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039468987","display_name":"Sam Liu","orcid":"https://orcid.org/0000-0003-2364-7774"},"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":"Sam Liu","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111565371","display_name":"Lin Fen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fen Lin","raw_affiliation_strings":["HP Labs, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109344676","display_name":"Yuhong Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhong Xiong","raw_affiliation_strings":["HP Labs, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Beijing, China","institution_ids":[]}]},{"author_position":"last","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","HP Labs, Palo ALto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"69"},"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":0.9771000146865845,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9606999754905701,"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":0.8396186828613281},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.7031349539756775},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6145492196083069},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5847318172454834},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.521098256111145},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.502514123916626},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.46227723360061646},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.4557570517063141},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4469701647758484},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.44324055314064026},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4242456555366516},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.42115071415901184},{"id":"https://openalex.org/keywords/longest-common-subsequence-problem","display_name":"Longest common subsequence problem","score":0.41412973403930664},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40584030747413635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3574904203414917},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.27418261766433716},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.20501956343650818},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18586811423301697},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16893768310546875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8396186828613281},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.7031349539756775},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6145492196083069},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5847318172454834},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.521098256111145},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.502514123916626},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.46227723360061646},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.4557570517063141},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4469701647758484},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.44324055314064026},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4242456555366516},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.42115071415901184},{"id":"https://openalex.org/C120098539","wikidata":"https://www.wikidata.org/wiki/Q141001","display_name":"Longest common subsequence problem","level":2,"score":0.41412973403930664},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40584030747413635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3574904203414917},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.27418261766433716},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.20501956343650818},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18586811423301697},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16893768310546875},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1600193.1600208","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1509502258","https://openalex.org/W2051141368","https://openalex.org/W2140208587"],"related_works":["https://openalex.org/W2386492541","https://openalex.org/W2393874032","https://openalex.org/W2388186172","https://openalex.org/W2270615713","https://openalex.org/W1524745358","https://openalex.org/W2252501696","https://openalex.org/W1583355281","https://openalex.org/W1674850363","https://openalex.org/W42769285","https://openalex.org/W13111539"],"abstract_inverted_index":{"This":[0],"work":[1],"studies":[2],"the":[3,30,33,37,75,81,149,152,170,176,188],"problem":[4],"of":[5,18,77,80,89,106,121,151,166,183,190],"extracting":[6],"articles":[7],"from":[8,15],"Web":[9,21,95],"pages":[10],"for":[11,40,74,147],"better":[12,78],"printing.":[13],"Different":[14],"existing":[16],"approaches":[17],"article":[19,41,107,153,171],"extraction,":[20],"printing":[22],"poses":[23],"several":[24],"unique":[25],"requirements:":[26],"1)":[27,125],"Identifying":[28],"just":[29],"boundary":[31,150],"surrounding":[32],"text-body":[34],"is":[35,44,60,179],"not":[36,67],"ideal":[38],"solution":[39],"extraction.":[42],"It":[43,59],"highly":[45],"desirable":[46],"to":[47,62],"filter":[48],"out":[49],"some":[50],"uninformative":[51],"links":[52],"and":[53,94,115,185],"advertisements":[54],"within":[55],"this":[56],"boundary.":[57],"2)":[58,135],"necessary":[61],"identify":[63],"paragraphs,":[64],"which":[65],"may":[66],"be":[68,87],"readily":[69],"separated":[70],"as":[71],"DOM":[72,111],"nodes,":[73],"purpose":[76],"layout":[79],"article.":[82],"3)":[83,155],"Its":[84],"performance":[85],"should":[86],"independent":[88],"content":[90],"domains,":[91],"written":[92],"languages,":[93],"page":[96],"templates.":[97],"Toward":[98],"these":[99],"goals":[100],"we":[101],"propose":[102],"a":[103,126,136],"novel":[104],"method":[105,123,178],"extraction":[108],"using":[109],"both":[110],"(Document":[112],"Object":[113],"Model)":[114],"visual":[116],"features.":[117],"The":[118],"main":[119],"components":[120],"our":[122],"include:":[124],"text":[127,145,167,191],"segment/paragraph":[128],"identification":[129],"algorithm":[130],"based":[131,143,160],"on":[132,144,161],"line-breaking":[133],"features,":[134],"global":[137],"optimization":[138],"method,":[139],"Maximum":[140],"Scoring":[141],"Subsequence,":[142],"segments":[146,168],"identifying":[148],"body,":[154],"an":[156],"outlier":[157],"elimination":[158],"step":[159],"left":[162],"or":[163],"right":[164],"alignment":[165],"with":[169],"body.":[172],"Our":[173],"experiments":[174],"showed":[175],"proposed":[177],"effective":[180],"in":[181],"terms":[182],"precision":[184],"recall":[186],"at":[187],"level":[189],"segments.":[192]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}