{"id":"https://openalex.org/W2140636749","doi":"https://doi.org/10.1145/1150402.1150492","title":"Combining linguistic and statistical analysis to extract relations from web documents","display_name":"Combining linguistic and statistical analysis to extract relations from web documents","publication_year":2006,"publication_date":"2006-08-20","ids":{"openalex":"https://openalex.org/W2140636749","doi":"https://doi.org/10.1145/1150402.1150492","mag":"2140636749"},"language":"en","primary_location":{"id":"doi:10.1145/1150402.1150492","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1150402.1150492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5034994700","display_name":"Fabian M. Suchanek","orcid":"https://orcid.org/0000-0001-7189-2796"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Fabian M. Suchanek","raw_affiliation_strings":["Max-Planck-Institute for Computer Science, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max-Planck-Institute for Computer Science, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054845773","display_name":"Georgiana Ifrim","orcid":"https://orcid.org/0000-0002-8400-2972"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georgiana Ifrim","raw_affiliation_strings":["Max-Planck-Institute for Computer Science, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max-Planck-Institute for Computer Science, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088135366","display_name":"Gerhard Weikum","orcid":"https://orcid.org/0000-0003-4959-6098"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Weikum","raw_affiliation_strings":["Max-Planck-Institute for Computer Science, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max-Planck-Institute for Computer Science, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034994700"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":17.6977,"has_fulltext":false,"cited_by_count":187,"citation_normalized_percentile":{"value":0.99261613,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"712","last_page":"717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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":0.7835510969161987},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.7283608913421631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6824790835380554},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6786602139472961},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.661622941493988},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5641416311264038},{"id":"https://openalex.org/keywords/semantic-relation","display_name":"Semantic relation","score":0.4621383249759674},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4536355137825012},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.41945356130599976},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33549371361732483},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3220687508583069},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09998619556427002},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.08103132247924805},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06305819749832153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7835510969161987},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.7283608913421631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6824790835380554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6786602139472961},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.661622941493988},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5641416311264038},{"id":"https://openalex.org/C2988080768","wikidata":"https://www.wikidata.org/wiki/Q7095057","display_name":"Semantic relation","level":3,"score":0.4621383249759674},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4536355137825012},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.41945356130599976},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33549371361732483},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3220687508583069},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09998619556427002},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08103132247924805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06305819749832153},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1150402.1150492","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1150402.1150492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W18304122","https://openalex.org/W185844958","https://openalex.org/W200042785","https://openalex.org/W1480596212","https://openalex.org/W1489949474","https://openalex.org/W1502749598","https://openalex.org/W1521610788","https://openalex.org/W1524234997","https://openalex.org/W1537290314","https://openalex.org/W1540550673","https://openalex.org/W1574901103","https://openalex.org/W1579858888","https://openalex.org/W1661295559","https://openalex.org/W1846742003","https://openalex.org/W1965605789","https://openalex.org/W1971563386","https://openalex.org/W1986543644","https://openalex.org/W2012051528","https://openalex.org/W2038721957","https://openalex.org/W2059799772","https://openalex.org/W2060565333","https://openalex.org/W2063981788","https://openalex.org/W2066653224","https://openalex.org/W2068737686","https://openalex.org/W2074950806","https://openalex.org/W2075123415","https://openalex.org/W2101660833","https://openalex.org/W2103931177","https://openalex.org/W2115294179","https://openalex.org/W2115461474","https://openalex.org/W2124634352","https://openalex.org/W2134368421","https://openalex.org/W2136134253","https://openalex.org/W2138627627","https://openalex.org/W2142086811","https://openalex.org/W2143349571","https://openalex.org/W2149820823","https://openalex.org/W2158994553","https://openalex.org/W2162340487","https://openalex.org/W2167072947","https://openalex.org/W2167435923","https://openalex.org/W3003340012","https://openalex.org/W3089319657","https://openalex.org/W6675351563"],"related_works":["https://openalex.org/W4234874385","https://openalex.org/W2323648130","https://openalex.org/W2350997567","https://openalex.org/W2392969287","https://openalex.org/W2370384704","https://openalex.org/W2357087812","https://openalex.org/W2888033806","https://openalex.org/W2014288545","https://openalex.org/W112768223","https://openalex.org/W2976808399"],"abstract_inverted_index":{"The":[0],"World":[1],"Wide":[2],"Web":[3],"provides":[4],"a":[5,32,45,74,115],"nearly":[6],"endless":[7],"source":[8],"of":[9,31,44,97,118,127],"knowledge,":[10],"which":[11],"is":[12,55],"mostly":[13],"given":[14,33],"in":[15],"natural":[16],"language.":[17],"A":[18],"first":[19],"step":[20],"towards":[21],"exploiting":[22],"this":[23,53,81,86],"data":[24],"automatically":[25],"could":[26],"be":[27,107],"to":[28,56,65,70,73,76],"extract":[29],"pairs":[30,43],"semantic":[34,63],"relation":[35],"from":[36],"text":[37,58,99],"documents":[38],"-":[39],"for":[40,52,109],"example":[41],"all":[42],"person":[46],"and":[47,69,112],"her":[48],"birthdate.":[49],"One":[50],"strategy":[51],"task":[54],"find":[57,77],"patterns":[59],"that":[60,85],"express":[61],"the":[62,119,125],"relation,":[64],"generalize":[66],"these":[67],"patterns,":[68],"apply":[71],"them":[72],"corpus":[75],"new":[78],"pairs.":[79],"In":[80],"paper,":[82],"we":[83,113],"show":[84,124],"approach":[87,129],"profits":[88],"significantly":[89],"when":[90],"deep":[91],"linguistic":[92,104],"structures":[93,105],"are":[94],"used":[95],"instead":[96],"surface":[98],"patterns.":[100],"We":[101,123],"demonstrate":[102],"how":[103],"can":[106],"represented":[108],"machine":[110],"learning,":[111],"provide":[114],"theoretical":[116],"analysis":[117],"pattern":[120],"matching":[121],"approach.":[122],"benefits":[126],"our":[128,134],"by":[130],"extensive":[131],"experiments":[132],"with":[133],"prototype":[135],"system":[136],"LEILA.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}