{"id":"https://openalex.org/W2163072729","doi":"https://doi.org/10.1109/icde.2011.5767842","title":"Web-scale information extraction with vertex","display_name":"Web-scale information extraction with vertex","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2163072729","doi":"https://doi.org/10.1109/icde.2011.5767842","mag":"2163072729"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2011.5767842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data 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/A5069516740","display_name":"Pankaj Gulhane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pankaj Gulhane","raw_affiliation_strings":["Yahoo Research Laboratories, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research Laboratories, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080593271","display_name":"Amit Madaan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amit Madaan","raw_affiliation_strings":["Yahoo Research Laboratories, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research Laboratories, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065369619","display_name":"Rupesh Mehta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rupesh Mehta","raw_affiliation_strings":["Microsoft IDC, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft IDC, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109879969","display_name":"Jeyashankher Ramamirtham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeyashankher Ramamirtham","raw_affiliation_strings":["Yahoo Research Laboratories, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research Laboratories, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111717871","display_name":"Rajeev Rastogi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajeev Rastogi","raw_affiliation_strings":["Yahoo Research Laboratories, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research Laboratories, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049560935","display_name":"Sandeep Satpal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandeep Satpal","raw_affiliation_strings":["Microsoft IDC, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft IDC, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038858575","display_name":"Srinivasan H. Sengamedu","orcid":"https://orcid.org/0000-0003-1847-8398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivasan H Sengamedu","raw_affiliation_strings":["Yahoo Research Laboratories, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research Laboratories, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001061675","display_name":"Ashwin Tengli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashwin Tengli","raw_affiliation_strings":["Microsoft IDC, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft IDC, Bangalore, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025635791","display_name":"Charu Tiwari","orcid":"https://orcid.org/0000-0003-1106-2453"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charu Tiwari","raw_affiliation_strings":["Yahoo Research Laboratories, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research Laboratories, Bangalore, India","institution_ids":[]}]}],"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":88,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1209","last_page":"1220"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9878000020980835,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9801999926567078,"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":0.7667165994644165},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.6972877383232117},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5954174399375916},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5395819544792175},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47716253995895386},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4761624038219452},{"id":"https://openalex.org/keywords/vertex","display_name":"Vertex (graph theory)","score":0.44974756240844727},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4476883113384247},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.44137340784072876},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.43279507756233215},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4316405653953552},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.42489758133888245},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35038989782333374},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.31766849756240845},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.25057435035705566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.217890202999115},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15568435192108154},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.08380919694900513}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667165994644165},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.6972877383232117},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5954174399375916},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5395819544792175},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47716253995895386},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4761624038219452},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.44974756240844727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4476883113384247},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.44137340784072876},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.43279507756233215},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4316405653953552},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.42489758133888245},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35038989782333374},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.31766849756240845},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.25057435035705566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.217890202999115},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15568435192108154},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.08380919694900513},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2011.5767842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.453.9494","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.453.9494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.it.iitb.ac.in/~sandeep/papers/ICDE2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W136639676","https://openalex.org/W1484413656","https://openalex.org/W1553019137","https://openalex.org/W1616576116","https://openalex.org/W1973483159","https://openalex.org/W2002956097","https://openalex.org/W2089363549","https://openalex.org/W2104086170","https://openalex.org/W2115461474","https://openalex.org/W2115770258","https://openalex.org/W2121751007","https://openalex.org/W2134150392","https://openalex.org/W2143309843","https://openalex.org/W2152565070","https://openalex.org/W2153072229","https://openalex.org/W2171364811","https://openalex.org/W6605550956","https://openalex.org/W6628750762","https://openalex.org/W6633154970","https://openalex.org/W6675573929","https://openalex.org/W6680060327"],"related_works":["https://openalex.org/W2390183027","https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W3144508074","https://openalex.org/W2467186806","https://openalex.org/W2951920527","https://openalex.org/W2998827288","https://openalex.org/W36911888","https://openalex.org/W2076910790","https://openalex.org/W2376164011"],"abstract_inverted_index":{"Vertex":[0,22,104],"is":[1,80,105],"a":[2,24,36],"Wrapper":[3],"Induction":[4],"system":[5,79,108],"developed":[6],"at":[7,19,114],"Yahoo!":[8],"for":[9,29,45],"extracting":[10],"structured":[11,33],"records":[12,91],"from":[13,92],"template-based":[14],"Web":[15,20,37,96,115],"pages.":[16],"To":[17,98],"operate":[18],"scale,":[21],"employs":[23],"host":[25],"of":[26,101],"novel":[27],"algorithms":[28],"(1)":[30],"Grouping":[31],"similar":[32],"pages":[34,44],"in":[35,58,82],"site,":[38],"(2)":[39],"Picking":[40],"the":[41,99,106],"appropriate":[42],"sample":[43,67],"wrapper":[46],"inference,":[47],"(3)":[48],"Learning":[49],"XPath-based":[50],"extraction":[51,113],"rules":[52],"that":[53],"are":[54],"robust":[55],"to":[56,109],"variations":[57],"site":[59,63],"structure,":[60],"(4)":[61],"Detecting":[62],"changes":[64],"by":[65,74],"monitoring":[66],"pages,":[68],"and":[69,84],"(5)":[70],"Optimizing":[71],"editorial":[72],"costs":[73],"reusing":[75],"rules,":[76],"etc.":[77],"The":[78],"deployed":[81],"production":[83],"currently":[85],"extracts":[86],"more":[87,93],"than":[88,94],"250":[89],"million":[90],"200":[95],"sites.":[97],"best":[100],"our":[102],"knowledge,":[103],"first":[107],"do":[110],"high-precision":[111],"information":[112],"scale.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}