{"id":"https://openalex.org/W2075726969","doi":"https://doi.org/10.1145/1151454.1151484","title":"From HTML documents to web tables and rules","display_name":"From HTML documents to web tables and rules","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2075726969","doi":"https://doi.org/10.1145/1151454.1151484","mag":"2075726969"},"language":"en","primary_location":{"id":"doi:10.1145/1151454.1151484","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1151454.1151484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th international conference on Electronic commerce The new e-commerce: innovations for conquering current barriers, obstacles and limitations to conducting successful business on the internet - ICEC '06","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/A5048594908","display_name":"Kai Simon","orcid":null},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Kai Simon","raw_affiliation_strings":["Universit\u00e4t Freiburg, Freiburg i.Br., Germany"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Freiburg, Freiburg i.Br., Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113532644","display_name":"Georg Lausen","orcid":null},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Lausen","raw_affiliation_strings":["Universit\u00e4t Freiburg, Freiburg i.Br., Germany"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Freiburg, Freiburg i.Br., Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001111183","display_name":"Harold Boley","orcid":"https://orcid.org/0000-0002-8940-7469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harold Boley","raw_affiliation_strings":["Institute for Information Technology -- e-Business, Fredericton, NB, Canada"],"affiliations":[{"raw_affiliation_string":"Institute for Information Technology -- e-Business, Fredericton, NB, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048594908"],"corresponding_institution_ids":["https://openalex.org/I161046081"],"apc_list":null,"apc_paid":null,"fwci":1.7213,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.89069623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"125","last_page":"125"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.984000027179718,"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":0.9794999957084656,"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/computer-science","display_name":"Computer science","score":0.7497484087944031},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5428386926651001},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.516822874546051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497484087944031},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5428386926651001},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.516822874546051}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1151454.1151484","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1151454.1151484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th international conference on Electronic commerce The new e-commerce: innovations for conquering current barriers, obstacles and limitations to conducting successful business on the internet - ICEC '06","raw_type":"proceedings-article"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:5764332","is_oa":false,"landing_page_url":"https://nrc-publications.canada.ca/fra/voir/objet/?id=4b3ab6b5-8cb0-4ed8-838b-7ed43067e340","pdf_url":null,"source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","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":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W9087766","https://openalex.org/W1491423131","https://openalex.org/W1510305954","https://openalex.org/W1517661163","https://openalex.org/W1534503730","https://openalex.org/W1604428157","https://openalex.org/W1789985355","https://openalex.org/W2005646337","https://openalex.org/W2050513812","https://openalex.org/W2077397274","https://openalex.org/W2084130127","https://openalex.org/W2084812512","https://openalex.org/W2102489964","https://openalex.org/W2102998074","https://openalex.org/W2110785447","https://openalex.org/W2116031053","https://openalex.org/W2133669904","https://openalex.org/W2147430776"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,31,71,122],"browser-extending":[3],"Semantic":[4,124],"Web":[5,111],"extraction":[6],"system":[7],"that":[8],"maps":[9],"HTML":[10],"documents":[11],"to":[12,17,42,69,117],"tables":[13,59],"and,":[14],"where":[15],"possible,":[16],"rules.":[18],"First,":[19],"the":[20,48,50,57,95,119],"basic":[21],"data":[22,33],"extractor":[23,53],"ViPER":[24,55,115],"distills":[25],"and":[26,63,74,88,106,108],"reorganizes":[27],"semi-structured":[28],"information":[29],"into":[30],"tabular":[32],"structure,":[34],"which":[35],"can":[36,90],"again":[37],"be":[38,91],"browsed":[39],"and/or":[40],"submitted":[41],"further":[43],"machine":[44],"processing.":[45],"Second,":[46],"exemplifying":[47],"latter,":[49],"extended":[51],"knowledge":[52,79],"Rex":[54,114],"mines":[56],"resulting":[58,82],"for":[60],"structural":[61],"properties":[62],"functional":[64],"dependencies.":[65],"Rules":[66],"are":[67],"generated":[68],"obtain":[70],"more":[72],"compact":[73],"manageable,":[75],"often":[76],"also":[77],"enriched,":[78],"representation.":[80],"The":[81],"fully":[83],"structured":[84],"information,":[85],"RuleML-serialized":[86],"facts":[87],"rules,":[89],"stored":[92],"along":[93],"with":[94],"orginal":[96],"documents,":[97],"queried":[98],"by":[99],"rule":[100],"engines":[101],"such":[102],"as":[103],"OO":[104],"jDREW":[105],"FLORID,":[107],"interchanged":[109],"between":[110],"Services.":[112],"Thus":[113],"contributes":[116],"automating":[118],"construction":[120],"of":[121],"machine-processable":[123],"Web.":[125]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
