{"id":"https://openalex.org/W2808746993","doi":"https://doi.org/10.1145/3219819.3220017","title":"TruePIE","display_name":"TruePIE","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2808746993","doi":"https://doi.org/10.1145/3219819.3220017","mag":"2808746993"},"language":"en","primary_location":{"id":"doi:10.1145/3219819.3220017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3220017","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3220017","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3220017","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100350205","display_name":"Qi Li","orcid":"https://orcid.org/0000-0002-3136-2157"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074821819","display_name":"Meng Jiang","orcid":"https://orcid.org/0000-0002-3009-519X"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Jiang","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012260410","display_name":"Xikun Zhang","orcid":"https://orcid.org/0000-0002-8346-8594"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xikun Zhang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101458727","display_name":"Meng Qu","orcid":"https://orcid.org/0000-0003-2961-8413"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Qu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111630666","display_name":"Timothy Hanratty","orcid":null},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy P. Hanratty","raw_affiliation_strings":["US Army Research Laboratory, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US Army Research Laboratory, Baltimore, MD, USA","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781385","display_name":"Jing Gao","orcid":"https://orcid.org/0000-0001-5099-6991"},"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":false,"raw_author_name":"Jing Gao","raw_affiliation_strings":["University at Buffalo, Buffalo, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5343,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91782347,"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":"1675","last_page":"1684"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9995999932289124,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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":0.8511439561843872},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7359333038330078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5366826057434082},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.45656782388687134},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4507446885108948},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43887537717819214},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4323859214782715},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.4236138164997101},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42199862003326416},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4019133746623993},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3975098729133606},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1113453209400177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0826164186000824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8511439561843872},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7359333038330078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5366826057434082},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.45656782388687134},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4507446885108948},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43887537717819214},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4323859214782715},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.4236138164997101},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42199862003326416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4019133746623993},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3975098729133606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1113453209400177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0826164186000824},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3219819.3220017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3220017","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3220017","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3219819.3220017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3220017","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3220017","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1346049954","display_name":null,"funder_award_id":"1U54GM114838","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G1919596789","display_name":null,"funder_award_id":"1U54GM114838","funder_id":"https://openalex.org/F4320337376","funder_display_name":"NIH Clinical Center"},{"id":"https://openalex.org/G2104517209","display_name":null,"funder_award_id":"IIS-17-41317","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3339524276","display_name":null,"funder_award_id":"1U54GM114838","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3346663007","display_name":null,"funder_award_id":"grant 1U54GM114838","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G523448137","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5490100290","display_name":null,"funder_award_id":"HDTRA11810026","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G6015371281","display_name":null,"funder_award_id":"No. W911NF-09-2-0053","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G7113567543","display_name":null,"funder_award_id":"IIS-16-18481, IIS-17-04532, IIS-17-41317, IIS-17-47614, IIS-13-19973","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7561134949","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8175839138","display_name":null,"funder_award_id":"No. W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8851674072","display_name":null,"funder_award_id":"W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332186","display_name":"Defense Threat Reduction Agency","ror":"https://ror.org/04tz64554"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337376","display_name":"NIH Clinical Center","ror":"https://ror.org/04vfsmv21"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808746993.pdf","grobid_xml":"https://content.openalex.org/works/W2808746993.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1483236033","https://openalex.org/W1493490255","https://openalex.org/W1508977358","https://openalex.org/W1512387364","https://openalex.org/W1529731474","https://openalex.org/W1614298861","https://openalex.org/W1852412531","https://openalex.org/W2009591769","https://openalex.org/W2045517419","https://openalex.org/W2068737686","https://openalex.org/W2083545228","https://openalex.org/W2094625154","https://openalex.org/W2103931177","https://openalex.org/W2109718074","https://openalex.org/W2123442489","https://openalex.org/W2129629757","https://openalex.org/W2129842875","https://openalex.org/W2139722852","https://openalex.org/W2151803977","https://openalex.org/W2152135319","https://openalex.org/W2153579005","https://openalex.org/W2167187514","https://openalex.org/W2250635077","https://openalex.org/W2251913848","https://openalex.org/W2325923789","https://openalex.org/W2595918108"],"related_works":["https://openalex.org/W2072806201","https://openalex.org/W2024218563","https://openalex.org/W1517743118","https://openalex.org/W165215672","https://openalex.org/W2361218558","https://openalex.org/W2966867036","https://openalex.org/W2890045624","https://openalex.org/W4289493986","https://openalex.org/W3125565408","https://openalex.org/W3157910026"],"abstract_inverted_index":{"Pattern-based":[0],"methods":[1,212],"have":[2],"been":[3],"successful":[4],"in":[5,67],"information":[6,50,64,144,148],"extraction":[7],"and":[8,36,58,101,110,145,189,225],"NLP":[9],"research.":[10],"Previous":[11],"approaches":[12],"learn":[13],"the":[14,53,61,98,103,117,141,146,150,154,179,206,216],"quality":[15,167],"of":[16,29,38,43,63,149,156,174,215],"a":[17,23,77,172,198],"textual":[18,118],"pattern":[19,120,143,223,227],"as":[20],"relatedness":[21,57],"to":[22,52,106,134,181],"certain":[24],"task":[25],"based":[26,170],"on":[27,159,171,197,213],"statistics":[28],"its":[30],"individual":[31],"content":[32],"(e.g.,":[33],"length,":[34],"frequency)":[35],"hundreds":[37],"carefully-annotated":[39],"labels.":[40],"However,":[41],"patterns":[42,85,126,169,176,185,192],"good":[44],"content-quality":[45],"may":[46],"generate":[47,165],"heavily":[48],"conflicting":[49],"due":[51],"big":[54],"gap":[55],"between":[56],"correctness.":[59],"Evaluating":[60],"correctness":[62],"is":[65],"critical":[66],"(entity,":[68],"attribute,":[69],"value)-tuple":[70],"extraction.":[71,228],"In":[72],"this":[73],"work,":[74],"we":[75],"propose":[76],"novel":[78],"method,":[79],"called":[80],"TruePIE,":[81],"that":[82,125,205],"finds":[83],"reliable":[84,112,184,219,222],"which":[86],"can":[87,163],"extract":[88],"not":[89],"only":[90],"related":[91],"but":[92],"also":[93],"correct":[94],"information.":[95],"TruePIE":[96,162,208],"adopts":[97],"self-training":[99],"framework":[100],"repeats":[102],"training-predicting-extracting":[104],"process":[105],"gradually":[107],"discover":[108],"more":[109,111],"patterns.":[113],"To":[114,152],"better":[115],"represent":[116],"patterns,":[119],"embeddings":[121,138],"are":[122,131],"formulated":[123],"so":[124],"with":[127],"similar":[128],"semantic":[129],"meanings":[130],"embedded":[132],"closely":[133],"each":[135,214],"other.":[136],"The":[137],"jointly":[139],"consider":[140],"local":[142],"distributional":[147],"extractions.":[151],"conquer":[153],"challenge":[155],"lacking":[157],"supervision":[158],"patterns'":[160],"reliability,":[161],"automatically":[164],"high":[166],"training":[168],"couple":[173],"seed":[175],"by":[177],"applying":[178],"arity-constraints":[180],"distinguish":[182],"highly":[183,190],"(i.e.,":[186,193],"positive":[187],"patterns)":[188],"unreliable":[191],"negative":[194,226],"patterns).":[195],"Experiments":[196],"huge":[199],"news":[200],"dataset":[201],"(over":[202],"25GB)":[203],"demonstrate":[204],"proposed":[207],"significantly":[209],"outperforms":[210],"baseline":[211],"three":[217],"tasks:":[218],"tuple":[220],"extraction,":[221,224]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2018-06-29T00:00:00"}