{"id":"https://openalex.org/W32002537","doi":"https://doi.org/10.1147/jrd.2012.2186519","title":"Automatic knowledge extraction from documents","display_name":"Automatic knowledge extraction from documents","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W32002537","doi":"https://doi.org/10.1147/jrd.2012.2186519","mag":"32002537"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2012.2186519","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2012.2186519","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-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/A5033960992","display_name":"Jialu Fan","orcid":"https://orcid.org/0000-0001-7585-1166"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"J. Fan","raw_affiliation_strings":["IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Research, Division Thomas J. Watson Research Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Research, Division Thomas J. Watson Research Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111981539","display_name":"Aditya Kalyanpur","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Kalyanpur","raw_affiliation_strings":["IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Research, Division Thomas J. Watson Research Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Research, Division Thomas J. Watson Research Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006194860","display_name":"David Gondek","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. C. Gondek","raw_affiliation_strings":["IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Research, Division Thomas J. Watson Research Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Research, Division Thomas J. Watson Research Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073155779","display_name":"David Ferrucci","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. A. Ferrucci","raw_affiliation_strings":["IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Research, Division Thomas J. Watson Research Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Research, Division Thomas J. Watson Research Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033960992"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":21.8347,"has_fulltext":false,"cited_by_count":129,"citation_normalized_percentile":{"value":0.99518591,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"56","issue":"3.4","first_page":"5:1","last_page":"5:10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","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/T10215","display_name":"Semantic Web and Ontologies","score":0.9980000257492065,"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":0.8463084697723389},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.68318772315979},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.662409245967865},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.6424622535705566},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.5773089528083801},{"id":"https://openalex.org/keywords/open-knowledge-base-connectivity","display_name":"Open Knowledge Base Connectivity","score":0.5393905639648438},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.538074791431427},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5360470414161682},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5269994139671326},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.49181726574897766},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45768749713897705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4538038372993469},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4315509796142578},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4126015901565552},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.4118526875972748},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18918102979660034},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.10109016299247742},{"id":"https://openalex.org/keywords/personal-knowledge-management","display_name":"Personal knowledge management","score":0.09739390015602112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8463084697723389},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.68318772315979},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.662409245967865},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.6424622535705566},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.5773089528083801},{"id":"https://openalex.org/C29804473","wikidata":"https://www.wikidata.org/wiki/Q2025711","display_name":"Open Knowledge Base Connectivity","level":4,"score":0.5393905639648438},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.538074791431427},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5360470414161682},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5269994139671326},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.49181726574897766},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45768749713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4538038372993469},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4315509796142578},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4126015901565552},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.4118526875972748},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18918102979660034},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.10109016299247742},{"id":"https://openalex.org/C187572123","wikidata":"https://www.wikidata.org/wiki/Q2034224","display_name":"Personal knowledge management","level":3,"score":0.09739390015602112},{"id":"https://openalex.org/C169735623","wikidata":"https://www.wikidata.org/wiki/Q1430172","display_name":"Organizational learning","level":2,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1147/jrd.2012.2186519","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2012.2186519","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1489784312","https://openalex.org/W1512387364","https://openalex.org/W1516391399","https://openalex.org/W1579035156","https://openalex.org/W1599190556","https://openalex.org/W1694079474","https://openalex.org/W1965605789","https://openalex.org/W2022166150","https://openalex.org/W2035050715","https://openalex.org/W2038721957","https://openalex.org/W2039217078","https://openalex.org/W2100749152","https://openalex.org/W2104798349","https://openalex.org/W2106390866","https://openalex.org/W2107658650","https://openalex.org/W2115792525","https://openalex.org/W2129615379","https://openalex.org/W2130947465","https://openalex.org/W2131192836","https://openalex.org/W2153225416","https://openalex.org/W2158575857","https://openalex.org/W2171278097","https://openalex.org/W2401961673","https://openalex.org/W2607879133","https://openalex.org/W2791297471","https://openalex.org/W4235505822","https://openalex.org/W6636036866"],"related_works":["https://openalex.org/W2140138473","https://openalex.org/W2904591968","https://openalex.org/W2086580554","https://openalex.org/W2508944927","https://openalex.org/W2126191795","https://openalex.org/W2592721119","https://openalex.org/W2224286040","https://openalex.org/W1520100787","https://openalex.org/W2086066989","https://openalex.org/W2125479495"],"abstract_inverted_index":{"Access":[0],"to":[1,32,83],"a":[2,75,80,136],"large":[3,95,137],"amount":[4],"of":[5,24,29,37,74,97,110,125],"knowledge":[6,25,39,58,87,93,127,156],"is":[7,46,54,99,128,132,157],"critical":[8],"for":[9,15],"success":[10],"at":[11],"answering":[12],"open-domain":[13],"questions":[14],"DeepQA":[16,162],"systems":[17],"such":[18],"as":[19],"IBM":[20,161],"Watson\u2122.":[21],"Formal":[22],"representation":[23],"has":[26],"the":[27,85,111,152,160],"advantage":[28],"being":[30],"easy":[31],"reason":[33],"with,":[34],"but":[35],"acquisition":[36],"structured":[38],"in":[40,71,121],"open":[41],"domains":[42],"from":[43,94,107,135,145],"unstructured":[44],"data":[45],"often":[47],"difficult":[48],"and":[49,59,67,88,139],"expensive.":[50],"Our":[51],"central":[52],"hypothesis":[53],"that":[55],"shallow":[56,92,114,126],"syntactic":[57,86],"its":[60],"implied":[61,89],"semantics":[62,104,142],"can":[63,68],"be":[64,69],"easily":[65],"acquired":[66],"used":[70,158],"many":[72],"areas":[73],"question-answering":[76],"system.":[77,163],"We":[78,148],"take":[79],"two-stage":[81],"approach":[82],"extract":[84],"semantics.":[90],"First,":[91],"collections":[96],"documents":[98],"automatically":[100,112,133],"extracted.":[101],"Second,":[102],"additional":[103,141],"are":[105,143],"inferred":[106,144],"aggregate":[108,146],"statistics":[109],"extracted":[113,155],"knowledge.":[115],"In":[116],"this":[117],"paper,":[118],"we":[119],"describe":[120],"detail":[122],"what":[123],"kind":[124],"extracted,":[129],"how":[130,140],"it":[131],"done":[134],"corpus,":[138],"statistics.":[147],"also":[149],"briefly":[150],"discuss":[151],"various":[153],"ways":[154],"throughout":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":12}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}