{"id":"https://openalex.org/W1993141752","doi":"https://doi.org/10.1145/1935826.1935894","title":"Collective extraction from heterogeneous web lists","display_name":"Collective extraction from heterogeneous web lists","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W1993141752","doi":"https://doi.org/10.1145/1935826.1935894","mag":"1993141752"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935894","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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/A5018314576","display_name":"Ashwin Machanavajjhala","orcid":"https://orcid.org/0000-0003-1555-7330"},"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":"Ashwin Machanavajjhala","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/A5090842155","display_name":"Arun Iyer","orcid":"https://orcid.org/0000-0001-7377-7599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arun Shankar Iyer","raw_affiliation_strings":["Yahoo! Research, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Bangalore, India","institution_ids":[]}]},{"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/A5025202709","display_name":"Srujana Merugu","orcid":"https://orcid.org/0000-0001-7849-9743"},"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":"Srujana Merugu","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.132,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87570178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"445","last_page":"454"},"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":0.9933000206947327,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9818999767303467,"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/disk-formatting","display_name":"Disk formatting","score":0.9772520661354065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.806118369102478},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6372294425964355},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5580612421035767},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4830899238586426},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.46966469287872314},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4475117027759552},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.41516488790512085},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3776298761367798},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07983651757240295}],"concepts":[{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.9772520661354065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806118369102478},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6372294425964355},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5580612421035767},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4830899238586426},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.46966469287872314},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4475117027759552},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.41516488790512085},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3776298761367798},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07983651757240295},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1935826.1935894","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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":27,"referenced_works":["https://openalex.org/W50457125","https://openalex.org/W1494141893","https://openalex.org/W1498682480","https://openalex.org/W1553019137","https://openalex.org/W1585529040","https://openalex.org/W1761401273","https://openalex.org/W1766290689","https://openalex.org/W1971415141","https://openalex.org/W1973483159","https://openalex.org/W1984911948","https://openalex.org/W1991133427","https://openalex.org/W2022158118","https://openalex.org/W2029873015","https://openalex.org/W2052581258","https://openalex.org/W2074231493","https://openalex.org/W2092827762","https://openalex.org/W2104086170","https://openalex.org/W2108126629","https://openalex.org/W2124410446","https://openalex.org/W2124943418","https://openalex.org/W2134150392","https://openalex.org/W2135767707","https://openalex.org/W2143309843","https://openalex.org/W2145007893","https://openalex.org/W2150721933","https://openalex.org/W3004248957","https://openalex.org/W6633154970"],"related_works":["https://openalex.org/W4244466418","https://openalex.org/W2104062382","https://openalex.org/W2162878363","https://openalex.org/W2389021890","https://openalex.org/W2479325685","https://openalex.org/W4245101192","https://openalex.org/W2146588098","https://openalex.org/W3183791698","https://openalex.org/W36911888","https://openalex.org/W4385731361"],"abstract_inverted_index":{"Automatic":[0],"extraction":[1,39],"of":[2,19,26],"structured":[3],"records":[4],"from":[5],"inconsistently":[6],"formatted":[7],"lists":[8,15,29],"on":[9,56],"the":[10,24,38],"web":[11],"is":[12],"challenging:":[13],"different":[14],"present":[16],"disparate":[17],"sets":[18],"attributes":[20,32,52],"with":[21],"variations":[22],"in":[23],"ordering":[25],"attributes;":[27],"many":[28],"contain":[30],"additional":[31],"and":[33,41],"noise":[34],"that":[35],"can":[36],"confuse":[37],"process;":[40],"formatting":[42,55],"within":[43],"a":[44],"list":[45],"may":[46],"be":[47],"inconsistent":[48],"due":[49],"to":[50],"missing":[51],"or":[53],"manual":[54],"some":[57],"sites.":[58]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}