{"id":"https://openalex.org/W2002956097","doi":"https://doi.org/10.1145/1559845.1559882","title":"Robust web extraction","display_name":"Robust web extraction","publication_year":2009,"publication_date":"2009-06-29","ids":{"openalex":"https://openalex.org/W2002956097","doi":"https://doi.org/10.1145/1559845.1559882","mag":"2002956097"},"language":"en","primary_location":{"id":"doi:10.1145/1559845.1559882","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1559845.1559882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 ACM SIGMOD International Conference on Management of data","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/A5081323769","display_name":"Nilesh Dalvi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nilesh Dalvi","raw_affiliation_strings":["Yahoo! Research, Santa Clara, CA, USA","Yahoo! Research, Santa Clara , CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Research, Santa Clara , CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029571794","display_name":"Philip Bohannon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Bohannon","raw_affiliation_strings":["Yahoo! Research, Santa Clara, CA, USA","Yahoo! Research, Santa Clara , CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Research, Santa Clara , CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101544732","display_name":"Fei Sha","orcid":"https://orcid.org/0000-0002-9382-0010"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Sha","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","[University of Southern California Los, Angeles, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California Los, Angeles, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"335","last_page":"348"},"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":0.9948999881744385,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9793000221252441,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8389781713485718},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.7433363199234009},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6672624349594116},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.6224972009658813},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.5908617377281189},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4712802767753601},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.45242393016815186},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4430393576622009},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3917933404445648},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.370715856552124},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2603452205657959},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08031415939331055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389781713485718},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7433363199234009},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6672624349594116},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.6224972009658813},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.5908617377281189},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4712802767753601},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.45242393016815186},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4430393576622009},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3917933404445648},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.370715856552124},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2603452205657959},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08031415939331055},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1559845.1559882","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1559845.1559882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W136639676","https://openalex.org/W1479669738","https://openalex.org/W1493576607","https://openalex.org/W1505906253","https://openalex.org/W1523223774","https://openalex.org/W1526729636","https://openalex.org/W1553019137","https://openalex.org/W1602270052","https://openalex.org/W1800919879","https://openalex.org/W1976373002","https://openalex.org/W1978478796","https://openalex.org/W1998076865","https://openalex.org/W2023673418","https://openalex.org/W2053315290","https://openalex.org/W2065568440","https://openalex.org/W2089363549","https://openalex.org/W2093559286","https://openalex.org/W2104086170","https://openalex.org/W2115770258","https://openalex.org/W2115826669","https://openalex.org/W2116624620","https://openalex.org/W2133059197","https://openalex.org/W2148210463","https://openalex.org/W2151192680","https://openalex.org/W2157617239","https://openalex.org/W2163614729","https://openalex.org/W2166210475","https://openalex.org/W2566113627","https://openalex.org/W2613433911","https://openalex.org/W3015882749","https://openalex.org/W3029645440","https://openalex.org/W4293775970","https://openalex.org/W6633154970","https://openalex.org/W6681973738","https://openalex.org/W6683028276"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2076910790","https://openalex.org/W2275993472","https://openalex.org/W2155199173","https://openalex.org/W1544491176","https://openalex.org/W2185387300","https://openalex.org/W2363544243"],"abstract_inverted_index":{"On":[0],"script-generated":[1],"web":[2,58],"sites,":[3],"many":[4],"documents":[5],"share":[6],"common":[7],"HTML":[8],"tree":[9,26,81,101],"structure,":[10],"allowing":[11],"wrappers":[12,32],"to":[13,33,60,71,79],"effectively":[14],"extract":[15],"information":[16],"of":[17,42,57,65,85,88,98],"interest.":[18],"Of":[19],"course,":[20],"the":[21,25,77,80],"scripts":[22],"and":[23,36,67,95],"thus":[24],"structure":[27,82],"evolve":[28,103],"over":[29],"time,":[30],"causing":[31],"break":[34],"repeatedly,":[35],"resulting":[37],"in":[38],"a":[39,50,62,86],"high":[40],"cost":[41],"maintaining":[43],"wrappers.":[44],"In":[45],"this":[46,69],"paper,":[47],"we":[48,53],"explore":[49],"novel":[51],"approach:":[52],"use":[54,68],"temporal":[55],"snapshots":[56],"pages":[59],"develop":[61],"tree-edit":[63],"model":[64,70],"HTML,":[66],"improve":[72],"wrapper":[73],"construction.":[74],"We":[75],"view":[76],"changes":[78],"as":[83],"suppositions":[84],"series":[87],"edit":[89,107],"operations:":[90],"deleting":[91],"nodes,":[92],"inserting":[93],"nodes":[94],"substituting":[96],"labels":[97],"nodes.":[99],"The":[100],"structures":[102],"by":[104],"choosing":[105],"these":[106],"operations":[108],"stochastically.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
