{"id":"https://openalex.org/W2091855574","doi":"https://doi.org/10.1145/1600193.1600241","title":"Web document text and images extraction using DOM analysis and natural language processing","display_name":"Web document text and images extraction using DOM analysis and natural language processing","publication_year":2009,"publication_date":"2009-09-16","ids":{"openalex":"https://openalex.org/W2091855574","doi":"https://doi.org/10.1145/1600193.1600241","mag":"2091855574"},"language":"en","primary_location":{"id":"doi:10.1145/1600193.1600241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600241","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":"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/A5109204680","display_name":"Parag Joshi","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":true,"raw_author_name":"Parag Mulendra Joshi","raw_affiliation_strings":["Hewlett-Packard Laboratories, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","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":["Hewlett-Packard Laboratories, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109204680"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":4.4418,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95032233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"218","last_page":"221"},"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":0.9290000200271606,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9236000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8587026596069336},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7412998080253601},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5580797791481018},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5561505556106567},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.5434338450431824},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5244139432907104},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5131221413612366},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4535561203956604},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4227266311645508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23239505290985107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8587026596069336},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7412998080253601},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5580797791481018},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5561505556106567},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.5434338450431824},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5244139432907104},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5131221413612366},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4535561203956604},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4227266311645508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23239505290985107},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1600193.1600241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600241","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W4508078","https://openalex.org/W1803802947","https://openalex.org/W1927338256","https://openalex.org/W1988121588","https://openalex.org/W1989338554","https://openalex.org/W2005646337","https://openalex.org/W2012575882","https://openalex.org/W2019264297","https://openalex.org/W2140208587","https://openalex.org/W2140327372"],"related_works":["https://openalex.org/W36911888","https://openalex.org/W4385731361","https://openalex.org/W1837359179","https://openalex.org/W2165504147","https://openalex.org/W2897171874","https://openalex.org/W1987716395","https://openalex.org/W2012575882","https://openalex.org/W2544674189","https://openalex.org/W2550808318","https://openalex.org/W4346570"],"abstract_inverted_index":{"Web":[0],"has":[1,14],"emerged":[2],"as":[3],"the":[4,11,37,50,62,68,81,175,192],"most":[5],"important":[6],"source":[7],"of":[8,47,52,83,102,124,136,150],"information":[9,29,84],"in":[10,16,33,49,172,187,197],"world.":[12],"This":[13,77],"resulted":[15],"need":[17],"for":[18,113,134,169],"automated":[19],"software":[20,177],"components":[21],"to":[22,57,95,98,132,179,191,199],"analyze":[23],"web":[24,35,87,104],"pages":[25,36,88],"and":[26,106,128,157,184],"harvest":[27],"useful":[28],"from":[30,86,110],"them.":[31,76],"However,":[32],"typical":[34],"informative":[38],"content":[39,64,70,79,101,112,173,186],"is":[40,65,93],"surrounded":[41],"by":[42],"a":[43,103,141,181],"very":[44],"high":[45],"degree":[46],"noise":[48],"form":[51],"advertisements,":[53],"navigation":[54],"bars,":[55],"links":[56],"other":[58],"content,":[59],"etc.":[60],"Often":[61],"noisy":[63,78,111,201],"interspersed":[66],"with":[67],"main":[69,100],"leaving":[71],"no":[72],"clean":[73],"boundaries":[74],"between":[75],"makes":[80],"problem":[82],"harvesting":[85],"much":[89],"harder.":[90],"Therefore,":[91],"it":[92,109],"essential":[94],"be":[96],"able":[97],"identify":[99],"page":[105],"automatically":[107],"isolate":[108],"any":[114],"further":[115],"analysis.":[116],"Most":[117],"existing":[118],"approaches":[119,161],"rely":[120],"on":[121],"prior":[122,148],"knowledge":[123,149],"website":[125,151],"specific":[126,131],"templates":[127],"hand-crafted":[129],"rules":[130],"websites":[133],"extraction":[135],"relevant":[137],"content.":[138,202],"We":[139],"propose":[140],"generic":[142],"approach":[143],"that":[144,168],"does":[145],"not":[146],"require":[147],"templates.":[152],"While":[153],"HTML":[154],"DOM":[155],"analysis":[156,160],"visual":[158],"layout":[159],"have":[162],"sometimes":[163],"been":[164],"used,":[165],"we":[166],"believe":[167],"higher":[170],"accuracy":[171],"extraction,":[174],"analyzing":[176],"needs":[178],"mimic":[180],"human":[182],"user":[183],"understand":[185],"natural":[188],"language":[189],"similar":[190],"way":[193],"humans":[194],"intuitively":[195],"do":[196],"order":[198],"eliminate":[200]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
