{"id":"https://openalex.org/W2096496923","doi":"https://doi.org/10.1145/1007568.1007584","title":"Using the structure of Web sites for automatic segmentation of tables","display_name":"Using the structure of Web sites for automatic segmentation of tables","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2096496923","doi":"https://doi.org/10.1145/1007568.1007584","mag":"2096496923"},"language":"en","primary_location":{"id":"doi:10.1145/1007568.1007584","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","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/A5049634383","display_name":"Kristina Lerman","orcid":"https://orcid.org/0000-0002-5071-0575"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kristina Lerman","raw_affiliation_strings":["USC Information Sciences Institute, Marina del Rey, CA","USC Information Sciences Institute, Marina del rey, CA"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina del Rey, CA","institution_ids":[]},{"raw_affiliation_string":"USC Information Sciences Institute, Marina del rey, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086169451","display_name":"Lise Getoor","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lise Getoor","raw_affiliation_strings":["University of Maryland, College Park, MD"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045363082","display_name":"Steven Minton","orcid":"https://orcid.org/0000-0001-8640-2905"},"institutions":[{"id":"https://openalex.org/I2801840469","display_name":"Torch Technologies (United States)","ror":"https://ror.org/00nrhr905","country_code":"US","type":"company","lineage":["https://openalex.org/I2801840469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Minton","raw_affiliation_strings":["Fetch Technologies, Manhattan Beach, CA"],"affiliations":[{"raw_affiliation_string":"Fetch Technologies, Manhattan Beach, CA","institution_ids":["https://openalex.org/I2801840469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089542402","display_name":"Craig A. Knoblock","orcid":"https://orcid.org/0000-0002-6371-4807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Craig Knoblock","raw_affiliation_strings":["USC Information Sciences Institute, Marina del Rey, CA","USC Information Sciences Institute, Marina del rey, CA"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina del Rey, CA","institution_ids":[]},{"raw_affiliation_string":"USC Information Sciences Institute, Marina del rey, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049634383"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":41.9886,"has_fulltext":false,"cited_by_count":153,"citation_normalized_percentile":{"value":0.99732262,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"130"},"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":0.9919999837875366,"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/T11719","display_name":"Data Quality and Management","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8522708415985107},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6855111122131348},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6449716091156006},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5766295194625854},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5394557118415833},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5195746421813965},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49021464586257935},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.467564195394516},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.43179476261138916},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.41988396644592285},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2719922661781311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22228866815567017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8522708415985107},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6855111122131348},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6449716091156006},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5766295194625854},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5394557118415833},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5195746421813965},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49021464586257935},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.467564195394516},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.43179476261138916},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.41988396644592285},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2719922661781311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22228866815567017},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1007568.1007584","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.7200","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.7200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/integration/papers/lerman04-sigmod.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.8462","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.8462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/sigmodpods04/sigmod/pdf/r-653.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":38,"referenced_works":["https://openalex.org/W113372867","https://openalex.org/W147915457","https://openalex.org/W158800878","https://openalex.org/W1502320541","https://openalex.org/W1510164014","https://openalex.org/W1528056001","https://openalex.org/W1532254649","https://openalex.org/W1566499617","https://openalex.org/W1566926854","https://openalex.org/W1595439448","https://openalex.org/W1691409177","https://openalex.org/W1847465294","https://openalex.org/W1967830139","https://openalex.org/W1988217119","https://openalex.org/W2008272135","https://openalex.org/W2029873015","https://openalex.org/W2034797903","https://openalex.org/W2078206655","https://openalex.org/W2093559286","https://openalex.org/W2102733302","https://openalex.org/W2104086170","https://openalex.org/W2110575115","https://openalex.org/W2115770258","https://openalex.org/W2125838338","https://openalex.org/W2134164043","https://openalex.org/W2147880316","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W2163041183","https://openalex.org/W2166407869","https://openalex.org/W2170188121","https://openalex.org/W2406080254","https://openalex.org/W2560674852","https://openalex.org/W6605996854","https://openalex.org/W6631829563","https://openalex.org/W6635635861","https://openalex.org/W6685116542","https://openalex.org/W6828034933"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2083329789","https://openalex.org/W2076910790","https://openalex.org/W2275993472","https://openalex.org/W2155199173","https://openalex.org/W1544491176","https://openalex.org/W36911888"],"abstract_inverted_index":{"Many":[0],"Web":[1,59,77,113,133,144,254],"sites,":[2,145],"especially":[3],"those":[4],"that":[5,29,63,90,170,176],"dynamically":[6],"generate":[7],"HTML":[8],"pages":[9,186,201],"to":[10,32,105,162,187,220],"display":[11],"the":[12,21,44,58,72,95,127,132,139,180,206,222,232,244],"results":[13],"of":[14,23,46,55,57,97,110,131,142,182,246,252],"a":[15,150,153,156,163,210,237,250],"user's":[16],"query,":[17],"present":[18,147],"information":[19,36,98,148,168,190,197],"in":[20,43,71,86,158,179,189,236],"form":[22,45],"list":[24,151],"or":[25,152],"tables.":[26,114],"Current":[27],"tools":[28],"allow":[30],"applications":[31],"programmatically":[33],"extract":[34],"this":[35],"rely":[37,124],"heavily":[38],"on":[39,66,126,138,249],"user":[40,67,121],"input,":[41,122],"often":[42],"labeled":[47],"extracted":[48],"records.":[49],"The":[50,192,214],"sheer":[51],"size":[52],"and":[53,82,88,108,129,184,204,241],"rate":[54],"growth":[56],"make":[60],"any":[61,120],"solution":[62],"relies":[64,137],"primarily":[65],"input":[68],"is":[69],"infeasible":[70],"long":[73],"term.":[74],"Fortunately,":[75],"many":[76,143],"sites":[78],"contain":[79],"much":[80],"explicit":[81],"implicit":[83],"structure,":[84],"both":[85],"layout":[87,128],"content,":[89],"we":[91,242],"can":[92,230],"exploit":[93,231],"for":[94],"purpose":[96],"extraction.":[99,191],"This":[100],"paper":[101],"describes":[102],"an":[103],"approach":[104,136,229],"automatic":[106],"extraction":[107],"segmentation":[109,207],"records":[111],"from":[112],"Automatic":[115],"methods":[116],"do":[117],"not":[118],"require":[119],"but":[123],"solely":[125],"content":[130,181],"source.":[134],"Our":[135],"common":[140],"structure":[141,235],"which":[146],"as":[149,202],"table,":[154],"with":[155],"link":[157],"each":[159,228,247],"entry":[160],"leading":[161],"detail":[164,185,200],"page":[165],"containing":[166],"additional":[167,196],"about":[169],"item.":[171],"We":[172,225],"describe":[173],"two":[174],"algorithms":[175],"use":[177],"redundancies":[178],"table":[183],"aid":[188],"first":[193],"algorithm":[194,216,248],"encodes":[195],"provided":[198],"by":[199,208],"constraints":[203],"finds":[205],"solving":[209],"constraint":[211],"satisfaction":[212],"problem.":[213],"second":[215],"uses":[217],"probabilistic":[218],"inference":[219],"find":[221],"record":[223],"segmentation.":[224],"show":[226],"how":[227],"web":[233],"site":[234],"general,":[238],"domain-independent":[239],"manner,":[240],"demonstrate":[243],"effectiveness":[245],"set":[251],"twelve":[253],"sites.":[255]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}