{"id":"https://openalex.org/W2131208289","doi":"https://doi.org/10.1147/jrd.2012.2185901","title":"Textual resource acquisition and engineering","display_name":"Textual resource acquisition and engineering","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2131208289","doi":"https://doi.org/10.1147/jrd.2012.2185901","mag":"2131208289"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2012.2185901","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2012.2185901","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/A5027400178","display_name":"Jennifer Chu\u2010Carroll","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":"J. Chu-Carroll","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#"],"raw_orcid":null,"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/A5033960992","display_name":"Jialu Fan","orcid":"https://orcid.org/0000-0001-7585-1166"},"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":"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#"],"raw_orcid":null,"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/A5028227133","display_name":"Nico Schlaefer","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Schlaefer","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","School of Computer Science, Carnegie Mellon Univ., Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon Univ., Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041770151","display_name":"Wlodek Zadrozny","orcid":"https://orcid.org/0000-0003-4844-9117"},"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":"W. Zadrozny","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#"],"raw_orcid":null,"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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.8289,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.97321651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"56","issue":"3.4","first_page":"4:1","last_page":"4:11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T10260","display_name":"Software Engineering Research","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6321147084236145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5083670020103455},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3670358657836914},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.361308217048645},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.3612697124481201},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.05919063091278076}],"concepts":[{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6321147084236145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5083670020103455},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3670358657836914},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.361308217048645},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.3612697124481201},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.05919063091278076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1147/jrd.2012.2185901","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2012.2185901","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":24,"referenced_works":["https://openalex.org/W32002537","https://openalex.org/W37696276","https://openalex.org/W1485852130","https://openalex.org/W1551844433","https://openalex.org/W1694079474","https://openalex.org/W1980910426","https://openalex.org/W1991860612","https://openalex.org/W2000545282","https://openalex.org/W2008479441","https://openalex.org/W2028282769","https://openalex.org/W2039447541","https://openalex.org/W2099685860","https://openalex.org/W2099762194","https://openalex.org/W2106750491","https://openalex.org/W2131192836","https://openalex.org/W2152650683","https://openalex.org/W2158890594","https://openalex.org/W2164052363","https://openalex.org/W2182947637","https://openalex.org/W2396592669","https://openalex.org/W2916471545","https://openalex.org/W6605815150","https://openalex.org/W6633038691","https://openalex.org/W6676131551"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2293168934","https://openalex.org/W2997903470","https://openalex.org/W2366882215","https://openalex.org/W2806254788","https://openalex.org/W2374823395","https://openalex.org/W2144179818","https://openalex.org/W2358927215","https://openalex.org/W1941585394","https://openalex.org/W2347751889"],"abstract_inverted_index":{"A":[0],"key":[1],"requirement":[2],"for":[3,230,233],"high-performing":[4,107],"question-answering":[5],"(QA)":[6],"systems":[7,44],"is":[8,40,127,161,174],"access":[9],"to":[10,17,91,98,136,141,155,190],"high-quality":[11,100],"reference":[12,53],"corpora":[13,54],"from":[14,163,216],"which":[15,159],"answers":[16],"questions":[18],"can":[19,103,182],"be":[20,142],"hypothesized":[21],"and":[22,30,122,173,209,237,255],"evaluated.":[23],"However,":[24],"the":[25,58,68,87,156,180,192,195,225,244],"topic":[26,200],"of":[27,57,63,79,86,95,132,197,212,239,246],"source":[28,118,120,123,187],"acquisition":[29,126],"engineering":[31],"has":[32],"received":[33],"very":[34],"little":[35],"attention":[36],"so":[37],"far.":[38],"This":[39],"because":[41],"most":[42,183],"existing":[43,145,164,213],"were":[45],"developed":[46,114,229],"under":[47],"organized":[48],"evaluation":[49],"efforts":[50],"that":[51,102,179,227],"included":[52],"as":[55,167,205,207],"part":[56,85],"task":[59,62],"specification.":[60],"The":[61],"answering":[64],"Jeopardy!\u2122":[65],"questions,":[66],"on":[67,148,252,256],"other":[69],"hand,":[70],"does":[71],"not":[72],"come":[73],"with":[74],"such":[75],"a":[76,93,106,168,177],"well-circumscribed":[77],"set":[78,94],"relevant":[80],"resources.":[81,241],"Therefore,":[82],"it":[83],"became":[84],"IBM":[88,231],"Watson\u2122":[89],"effort":[90],"develop":[92],"well-defined":[96],"procedures":[97],"acquire":[99],"resources":[101,146],"effectively":[104],"support":[105],"QA":[108,258],"system.":[109],"To":[110],"this":[111,221],"end,":[112],"we":[113,223,228],"three":[115],"procedures,":[116],"i.e.,":[117],"acquisition,":[119,235],"transformation,":[121,236],"expansion.":[124],"Source":[125,152],"an":[128],"iterative":[129],"development":[130],"process":[131,157],"acquiring":[133],"new":[134,203],"collections":[135],"cover":[137],"salient":[138],"topics":[139],"deemed":[140],"gaps":[143],"in":[144,158,171,176,194],"based":[147],"principled":[149],"error":[150],"analysis.":[151],"transformation":[153],"refers":[154],"information":[160,204,214],"extracted":[162,215],"sources,":[165],"either":[166],"whole":[169],"or":[170],"part,":[172],"represented":[175],"form":[178],"system":[181],"easily":[184],"use.":[185],"Finally,":[186],"expansion":[188,238],"attempts":[189],"increase":[191],"coverage":[193],"content":[196],"each":[198,247],"known":[199],"by":[201],"adding":[202],"well":[206],"lexical":[208],"syntactic":[210],"variations":[211],"external":[217],"large":[218],"collections.":[219],"In":[220],"paper,":[222],"discuss":[224],"methodology":[226],"Watson":[232],"performing":[234],"textual":[240],"We":[242],"demonstrate":[243],"effectiveness":[245],"technique":[248],"through":[249],"its":[250],"impact":[251],"candidate":[253],"recall":[254],"end-to-end":[257],"performance.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}