{"id":"https://openalex.org/W2421306863","doi":"https://doi.org/10.1145/2882903.2915214","title":"Robust and Noise Resistant Wrapper Induction","display_name":"Robust and Noise Resistant Wrapper Induction","publication_year":2016,"publication_date":"2016-06-14","ids":{"openalex":"https://openalex.org/W2421306863","doi":"https://doi.org/10.1145/2882903.2915214","mag":"2421306863"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2915214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/74cf2757-521b-4d21-9135-fc69f6708329","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113511969","display_name":"Tim Furche","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tim Furche","raw_affiliation_strings":["Oxford University, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024566364","display_name":"Jinsong Guo","orcid":"https://orcid.org/0000-0002-1142-3610"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinsong Guo","raw_affiliation_strings":["Oxford University, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010785818","display_name":"Sebastian Maneth","orcid":"https://orcid.org/0000-0001-8667-5436"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sebastian Maneth","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051365299","display_name":"Christian Schallhart","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christian Schallhart","raw_affiliation_strings":["Oxford University, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113511969"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":5.5429,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.95840599,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"773","last_page":"784"},"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/T11719","display_name":"Data Quality and Management","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9932000041007996,"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":0.8612306714057922},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.791006863117218},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7861344814300537},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6448346972465515},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5742422938346863},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5373289585113525},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5235604643821716},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4586936831474304},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4450171887874603},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3753318786621094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27055174112319946},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.22016620635986328},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16601219773292542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8612306714057922},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.791006863117218},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7861344814300537},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6448346972465515},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5742422938346863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5373289585113525},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5235604643821716},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4586936831474304},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4450171887874603},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3753318786621094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27055174112319946},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.22016620635986328},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16601219773292542},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2882903.2915214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:b31073dc-d63c-47e7-9fc2-e7b94d3228f1","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:b31073dc-d63c-47e7-9fc2-e7b94d3228f1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements at Oxford","raw_type":"Conference"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/74cf2757-521b-4d21-9135-fc69f6708329","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/74cf2757-521b-4d21-9135-fc69f6708329","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Furche, T, Guo, J, Maneth, S & Schallhart, C 2016, Robust and Noise Resistant Wrapper Induction. in SIGMOD '16 Proceedings of the 2016 International Conference on Management of Data. pp. 773-784, 2016 International Conference on Management of Data, San Francisco, California, United States, 26/06/16. https://doi.org/10.1145/2882903.2915214","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/74cf2757-521b-4d21-9135-fc69f6708329","is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=2915214","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/74cf2757-521b-4d21-9135-fc69f6708329","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/74cf2757-521b-4d21-9135-fc69f6708329","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Furche, T, Guo, J, Maneth, S & Schallhart, C 2016, Robust and Noise Resistant Wrapper Induction. in SIGMOD '16 Proceedings of the 2016 International Conference on Management of Data. pp. 773-784, 2016 International Conference on Management of Data, San Francisco, California, United States, 26/06/16. https://doi.org/10.1145/2882903.2915214","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1242154315","display_name":null,"funder_award_id":"641222","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G8298339663","display_name":"VADA: Value Added Data Systems -- Principles and Architecture","funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8400180575","display_name":null,"funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W279841946","https://openalex.org/W1494141893","https://openalex.org/W1531487010","https://openalex.org/W1553019137","https://openalex.org/W1567298333","https://openalex.org/W1971415141","https://openalex.org/W2002956097","https://openalex.org/W2035302703","https://openalex.org/W2037959103","https://openalex.org/W2069205071","https://openalex.org/W2080132606","https://openalex.org/W2084801987","https://openalex.org/W2096765155","https://openalex.org/W2097874932","https://openalex.org/W2100965097","https://openalex.org/W2111278149","https://openalex.org/W2120101509","https://openalex.org/W2120170839","https://openalex.org/W2148210463","https://openalex.org/W2148317291","https://openalex.org/W2160189941","https://openalex.org/W2170477095","https://openalex.org/W2296164608","https://openalex.org/W3000265418","https://openalex.org/W6633154970","https://openalex.org/W6681973738"],"related_works":["https://openalex.org/W1542110834","https://openalex.org/W2611888112","https://openalex.org/W2121120069","https://openalex.org/W562932586","https://openalex.org/W2124793519","https://openalex.org/W2398280235","https://openalex.org/W2184735843","https://openalex.org/W2355446901","https://openalex.org/W1994081385","https://openalex.org/W2346169362"],"abstract_inverted_index":{"Wrapper":[0],"induction":[1,64,143],"is":[2,82,87,138,210],"the":[3,15,24,33,39,58,63,108,154,168,174,181,197,201,213,222],"problem":[4],"of":[5,14,55,119,191,200,221],"automatically":[6],"inferring":[7],"a":[8,52,83,115,127,135],"query":[9,19,84],"from":[10,158],"annotated":[11,25],"web":[12,59,159],"pages":[13,160],"same":[16,34],"template.":[17,35],"This":[18,209],"should":[20,48,66],"not":[21],"only":[22],"select":[23,107],"content":[26,31],"accurately":[27,37],"but":[28,94],"also":[29],"other":[30],"following":[32],"Beyond":[36],"matching":[38],"template,":[40],"we":[41],"consider":[42],"two":[43],"additional":[44],"requirements:":[45],"(1)":[46],"wrappers":[47,105],"be":[49,67,102],"robust":[50,147,179],"against":[51,230],"large":[53],"class":[54],"changes":[56,195,205],"to":[57,79,90,97,101,134,196,212,234,240],"pages,":[60],"and":[61,121,148,171,215,236],"(2)":[62],"process":[65],"noise":[68,149,232,238],"resistant,":[69],"i.e.,":[70],"tolerate":[71],"slightly":[72],"erroneous":[73],"(e.g.,":[74],"machine":[75],"generated)":[76],"samples.":[77],"Key":[78],"our":[80,141],"approach":[81],"language":[85,116],"that":[86,106,123,161,173],"powerful":[88],"enough":[89,96],"permit":[91],"accurate":[92],"selection,":[93],"limited":[95],"force":[98],"noisy":[99],"samples":[100],"generalized":[103],"into":[104],"likely":[109],"intended":[110],"items.":[111],"We":[112,152],"introduce":[113],"such":[114,126],"as":[117,165,178,180],"subset":[118],"XPATH":[120],"show":[122,172],"even":[124],"for":[125],"restricted":[128],"language,":[129],"inducing":[130],"optimal":[131],"queries":[132,155,176,185,226],"according":[133],"suitable":[136],"scoring":[137],"infeasible.":[139],"Nevertheless,":[140],"wrapper":[142],"framework":[144],"infers":[145],"highly":[146,228],"resistant":[150,229],"queries.":[151,183,224],"evaluate":[153],"on":[156,206],"snapshots":[157],"change":[162],"over":[163],"time":[164],"provided":[166],"by":[167],"Internet":[169],"Archive,":[170],"induced":[175],"are":[177,227],"human-made":[182],"The":[184,225],"often":[186],"survive":[187],"hundreds":[188],"sometimes":[189],"thousands":[190],"days,":[192],"with":[193],"many":[194],"relative":[198],"position":[199],"selected":[202],"nodes":[203,220],"(including":[204],"template":[207],"level).":[208],"due":[211],"few":[214],"discriminative":[216],"anchor":[217],"(intermediately":[218],"selected)":[219],"generated":[223],"positive":[231],"(up":[233,239],"50%)":[235],"negative":[237],"20%).":[241]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}