{"id":"https://openalex.org/W2137216273","doi":"https://doi.org/10.1145/1963192.1963251","title":"Web information extraction using Markov logic networks","display_name":"Web information extraction using Markov logic networks","publication_year":2011,"publication_date":"2011-03-28","ids":{"openalex":"https://openalex.org/W2137216273","doi":"https://doi.org/10.1145/1963192.1963251","mag":"2137216273"},"language":"en","primary_location":{"id":"doi:10.1145/1963192.1963251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion on World wide web","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/A5043060774","display_name":"Sandeepkumar 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":"Sandeepkumar Satpal","raw_affiliation_strings":["Microsoft, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007508220","display_name":"Sahely Bhadra","orcid":"https://orcid.org/0000-0002-7453-9880"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sahely Bhadra","raw_affiliation_strings":["CSA, Indian Institute of Science, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSA, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111436183","display_name":"Sundararajan Sellamanickam","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sundararajan Sellamanickam","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111717871","display_name":"Rajeev Rastogi","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rajeev Rastogi","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105422045","display_name":"Prithviraj Sen","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Prithviraj Sen","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0795,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92351343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"116"},"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":0.9883000254631042,"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/T11106","display_name":"Data Management and Algorithms","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/inference","display_name":"Inference","score":0.8274372816085815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7323012351989746},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5967682600021362},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5636041164398193},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.464553564786911},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4622151255607605},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45074138045310974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40082380175590515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3707532286643982},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12442612648010254}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8274372816085815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7323012351989746},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5967682600021362},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5636041164398193},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.464553564786911},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4622151255607605},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45074138045310974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40082380175590515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3707532286643982},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12442612648010254}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1963192.1963251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion on World wide web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W121830907","https://openalex.org/W124040947","https://openalex.org/W1538211826","https://openalex.org/W1553019137","https://openalex.org/W1616576116","https://openalex.org/W1973483159","https://openalex.org/W1977970897","https://openalex.org/W2029873015","https://openalex.org/W2098678088","https://openalex.org/W2104086170","https://openalex.org/W2124410446","https://openalex.org/W2130944959","https://openalex.org/W2134150392","https://openalex.org/W2143309843","https://openalex.org/W2145007893","https://openalex.org/W2154445423","https://openalex.org/W2171364811","https://openalex.org/W2913389685","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1660242800","https://openalex.org/W2077211377","https://openalex.org/W1006270037","https://openalex.org/W3152686072","https://openalex.org/W2611741382","https://openalex.org/W3135843367","https://openalex.org/W3129238073","https://openalex.org/W36911888","https://openalex.org/W4385731361"],"abstract_inverted_index":{"In":[0],"this":[1,51],"paper,":[2],"we":[3],"consider":[4],"the":[5,18,26,74,85,111],"problem":[6],"of":[7,20,28,73,104,113],"extracting":[8],"structured":[9],"data":[10],"from":[11],"web":[12],"pages":[13,29],"taking":[14],"into":[15],"account":[16],"both":[17,40],"content":[19,41],"individual":[21],"attributes":[22],"as":[23,25],"well":[24],"structure":[27],"and":[30,42,50],"sites.":[31],"We":[32,59,79],"use":[33],"Markov":[34],"Logic":[35],"Networks":[36],"(MLNs)":[37],"to":[38,54,69],"capture":[39],"structural":[43],"features":[44],"in":[45,63],"a":[46],"single":[47],"unified":[48],"framework,":[49],"enables":[52],"us":[53],"perform":[55],"more":[56,92],"accurate":[57],"inference.":[58],"show":[60],"that":[61,89,101],"inference":[62,97],"our":[64,114],"information":[65],"extraction":[66],"scenario":[67],"reduces":[68],"solving":[70,84],"an":[71],"instance":[72],"maximum":[75,86],"weight":[76],"subgraph":[77,87],"problem.":[78],"develop":[80],"specialized":[81],"procedures":[82],"for":[83,99],"variants":[88,103],"are":[90],"far":[91],"efficient":[93],"than":[94],"previously":[95],"proposed":[96],"methods":[98],"MLNs":[100],"solve":[102],"MAX-SAT.":[105],"Experiments":[106],"with":[107],"real-life":[108],"datasets":[109],"demonstrate":[110],"effectiveness":[112],"approach.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}