{"id":"https://openalex.org/W2174011386","doi":"https://doi.org/10.1017/s1351324906004116","title":"InfoXtract: A customizable intermediate level information extraction engine","display_name":"InfoXtract: A customizable intermediate level information extraction engine","publication_year":2006,"publication_date":"2006-06-09","ids":{"openalex":"https://openalex.org/W2174011386","doi":"https://doi.org/10.1017/s1351324906004116","mag":"2174011386"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324906004116","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324906004116","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","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/A5063869451","display_name":"Rohini K. Srihari","orcid":"https://orcid.org/0000-0001-7454-6872"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"ROHINI K. SRIHARI","raw_affiliation_strings":["Janya Inc., 1408 Sweet Home Road, Amherst, NY 14228, USA, State University of New York at Buffalo e-mail:"],"affiliations":[{"raw_affiliation_string":"Janya Inc., 1408 Sweet Home Road, Amherst, NY 14228, USA, State University of New York at Buffalo e-mail:","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318448","display_name":"Wei Li","orcid":"https://orcid.org/0000-0003-4242-1615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"WEI LI","raw_affiliation_strings":["Janya Inc., 1408 Sweet Home Road, Amherst, NY 14228, USA e-mail:"],"affiliations":[{"raw_affiliation_string":"Janya Inc., 1408 Sweet Home Road, Amherst, NY 14228, USA e-mail:","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044873724","display_name":"Thomas L. Cornell","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"THOMAS CORNELL","raw_affiliation_strings":["Janya Inc., 1408 Sweet Home Road, Amherst, NY 14228, USA e-mail:"],"affiliations":[{"raw_affiliation_string":"Janya Inc., 1408 Sweet Home Road, Amherst, NY 14228, USA e-mail:","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111632482","display_name":"Cheng Niu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"CHENG NIU","raw_affiliation_strings":["Microsoft Research China, 5/F, Beijing Sigma Center, No. 49, Zhichun Road, Haidian District, Beijing100080, P.R.C. e-mail:"],"affiliations":[{"raw_affiliation_string":"Microsoft Research China, 5/F, Beijing Sigma Center, No. 49, Zhichun Road, Haidian District, Beijing100080, P.R.C. e-mail:","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063869451"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":13.0404,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.98755489,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"14","issue":"1","first_page":"33","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9980999827384949,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9980999827384949,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9973999857902527,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.9199163913726807},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6555894613265991},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5727514624595642},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5484569072723389},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5107607841491699},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.483318567276001},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.465945839881897},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34617191553115845},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1817701756954193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9199163913726807},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6555894613265991},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5727514624595642},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5484569072723389},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5107607841491699},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.483318567276001},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.465945839881897},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34617191553115845},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1817701756954193},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1017/s1351324906004116","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324906004116","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:ADA457779","is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA457779","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","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":"DTIC","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.2054","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.2054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://tangra.si.umich.edu/clair/HLT-NAACL03/sealts/pdf/Srihari_NAACL_2003_SEALTS_paper2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.4101","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.4101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/W/W03/W03-0808.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.8378","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.8378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cedar.buffalo.edu/~rohini/Papers/JNLE14-Infoxtract.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W30314283","https://openalex.org/W197270748","https://openalex.org/W1520377376","https://openalex.org/W1535549842","https://openalex.org/W1571327583","https://openalex.org/W1588383342","https://openalex.org/W1606142945","https://openalex.org/W1984061923","https://openalex.org/W1987709131","https://openalex.org/W1990444882","https://openalex.org/W1991383860","https://openalex.org/W2026147653","https://openalex.org/W2029915058","https://openalex.org/W2054114339","https://openalex.org/W2093476618","https://openalex.org/W2113227740","https://openalex.org/W2124634352","https://openalex.org/W2126069159","https://openalex.org/W2126637410","https://openalex.org/W2131010894","https://openalex.org/W2142928985","https://openalex.org/W2145250483","https://openalex.org/W2159176464","https://openalex.org/W2432471317","https://openalex.org/W2599848827","https://openalex.org/W2786175397","https://openalex.org/W2911295106","https://openalex.org/W4211152277","https://openalex.org/W4252090733","https://openalex.org/W4254240410","https://openalex.org/W4285719527","https://openalex.org/W6633930187"],"related_works":["https://openalex.org/W4388311650","https://openalex.org/W1974056099","https://openalex.org/W4245343541","https://openalex.org/W2386077341","https://openalex.org/W563589758","https://openalex.org/W5922282","https://openalex.org/W2954004777","https://openalex.org/W2949638731","https://openalex.org/W2951102138","https://openalex.org/W2165268584"],"abstract_inverted_index":{"Abstract":[0],"Information":[1],"Extraction":[2],"(IE)":[3],"systems":[4,47],"assist":[5],"analysts":[6],"to":[7,20,48,78,139,204,210,242],"assimilate":[8],"information":[9,22,26,173,212],"from":[10,235],"electronic":[11],"documents.":[12],"This":[13,55,124],"paper":[14,125],"focuses":[15],"on":[16,82,165],"IE":[17,46,62,95,133,145,237],"tasks":[18,96,146,229],"designed":[19],"support":[21],"discovery":[23,27],"applications.":[24],"Since":[25],"implies":[28,56,87],"examining":[29],"large":[30],"volumes":[31],"of":[32,150,155,233,250],"heterogeneous":[33],"documents":[34,183],"for":[35,59,69,90,262],"situations":[36],"that":[37,64,97,135,205],"cannot":[38],"be":[39,67,75,137],"anticipated":[40],"a":[41,60,129,175,179,185],"priori":[42],",":[43,128],"they":[44],"require":[45],"have":[49],"breadth":[50],"as":[51,53,111,113,148,196,198,214,219,221],"well":[52,197,220],"depth.":[54],"the":[57,80,88,101,114,119,231,263,269],"need":[58,89],"domain-independent":[61],"system":[63,81],"can":[65,136],"easily":[66],"customized":[68],"specific":[70],"domains:":[71],"end":[72],"users":[73],"must":[74],"given":[76],"tools":[77],"customize":[79],"their":[83],"own.":[84],"It":[85,142],"also":[86],"defining":[91],"new":[92,144,228],"intermediate":[93],"level":[94],"are":[98,271],"richer":[99],"than":[100],"subject-verb-object":[102],"(SVO)":[103],"triples":[104],"produced":[105],"by":[106,118],"shallow":[107],"systems,":[108],"yet":[109],"not":[110],"complex":[112],"domain-specific":[115],"scenarios":[116],"defined":[117],"Message":[120],"Understanding":[121],"Conference":[122],"(MUC).":[123],"describes":[126,143],"InfoXtract":[127],"robust,":[130],"scalable,":[131],"intermediate-level":[132],"engine":[134,238,265,270],"ported":[138],"various":[140],"domains.":[141],"such":[147,213],"synthesis":[149],"entity":[151],"profiles,":[152],"and":[153,181,193,201,253,266],"extraction":[154],"concept-based":[156],"general":[157],"events":[158,202,208],"which":[159],"represent":[160],"realistic":[161],"near-term":[162],"goals":[163],"focused":[164],"deriving":[166],"useful,":[167],"actionable":[168],"information.":[169],"Entity":[170],"profiles":[171],"consolidate":[172],"about":[174],"person/organization/location":[176],"etc.":[177],"within":[178],"document":[180],"across":[182],"into":[184,190],"single":[186],"template;":[187],"this":[188],"takes":[189],"account":[191],"aliases":[192],"anaphoric":[194],"references":[195,224],"key":[199],"relationships":[200],"pertaining":[203],"entity.":[206],"Concept-based":[207],"attempt":[209],"normalize":[211],"time":[215],"expressions":[216],"(e.g.,":[217,225],"yesterday)":[218],"ambiguous":[222],"location":[223],"Buffalo).":[226],"These":[227],"facilitate":[230],"correlation":[232],"output":[234],"an":[236],"with":[239],"structured":[240],"data":[241],"enable":[243],"text":[244],"mining.":[245],"InfoXtract's":[246],"hybrid":[247],"architecture":[248],"comprised":[249],"grammatical":[251],"processing":[252],"machine":[254],"learning":[255],"is":[256],"described":[257],"in":[258],"detail.":[259],"Benchmarking":[260],"results":[261],"core":[264],"applications":[267],"utilizing":[268],"presented.":[272]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"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":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}