{"id":"https://openalex.org/W2890487780","doi":"https://doi.org/10.18653/v1/d18-1405","title":"Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency","display_name":"Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890487780","doi":"https://doi.org/10.18653/v1/d18-1405","mag":"2890487780"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1405","pdf_url":"https://www.aclweb.org/anthology/D18-1405.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1405.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077607729","display_name":"Zhuang Ma","orcid":"https://orcid.org/0000-0002-7286-1155"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuang Ma","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079061237","display_name":"Michael Collins","orcid":"https://orcid.org/0000-0003-0997-1527"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Collins","raw_affiliation_strings":["Google AI Language and Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google AI Language and Columbia University","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2063,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.96738585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3698","last_page":"3707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9927999973297119,"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":0.9927999973297119,"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":0.9886999726295471,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9714999794960022,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6692314147949219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6313275098800659},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5943877696990967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5213276743888855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46808061003685},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43457964062690735},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37369704246520996},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3620213270187378},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35249364376068115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3275817632675171},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10385462641716003}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6692314147949219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6313275098800659},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5943877696990967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5213276743888855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46808061003685},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43457964062690735},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37369704246520996},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3620213270187378},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35249364376068115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3275817632675171},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10385462641716003}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1405","pdf_url":"https://www.aclweb.org/anthology/D18-1405.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1405","pdf_url":"https://www.aclweb.org/anthology/D18-1405.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890487780.pdf","grobid_xml":"https://content.openalex.org/works/W2890487780.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1591801644","https://openalex.org/W1632114991","https://openalex.org/W2096175520","https://openalex.org/W2120861206","https://openalex.org/W2125031621","https://openalex.org/W2138204974","https://openalex.org/W2147880316","https://openalex.org/W2152808281","https://openalex.org/W2153579005","https://openalex.org/W2259472270","https://openalex.org/W2963537482","https://openalex.org/W4229628595","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2915512527","https://openalex.org/W2798198862","https://openalex.org/W51364034","https://openalex.org/W2798997222","https://openalex.org/W2793336762","https://openalex.org/W2091548507","https://openalex.org/W2368816706","https://openalex.org/W1546381263"],"abstract_inverted_index":{"Noise":[0],"Contrastive":[1],"Estimation":[2],"(NCE)":[3],"is":[4,35],"a":[5,27,67,107,114],"powerful":[6],"parameter":[7,127],"estimation":[8,51],"method":[9],"for":[10,101],"loglinear":[11],"models,":[12],"which":[13],"avoids":[14],"calculation":[15],"of":[16,52,71,99,123,141,147,164],"the":[17,90,110,120,133,138,142,160],"partition":[18],"function":[19],"or":[20],"its":[21],"derivatives":[22],"at":[23],"each":[24],"training":[25],"step,":[26],"computationally":[28],"demanding":[29],"step":[30],"in":[31,45,60,73],"many":[32],"cases.":[33],"It":[34],"closely":[36],"related":[37],"to":[38,89],"negative":[39],"sampling":[40],"methods,":[41],"now":[42],"widely":[43],"used":[44],"NLP.":[46],"This":[47],"paper":[48],"considers":[49],"NCE-based":[50],"conditional":[53,91,102],"models.":[54],"Conditional":[55],"models":[56],"are":[57,81],"frequently":[58],"encountered":[59],"practice;":[61],"however":[62],"there":[63,80],"has":[64],"not":[65],"been":[66],"rigorous":[68],"theoretical":[69],"analysis":[70],"NCE":[72,88,100,124],"this":[74],"setting,":[75],"and":[76,144,156,162],"we":[77,95,136,150],"will":[78],"argue":[79],"subtle":[82],"but":[83],"important":[84],"questions":[85],"when":[86],"generalizing":[87],"case.":[92],"In":[93],"particular,":[94],"analyze":[96,137],"two":[97],"variants":[98,146],"models:":[103],"one":[104],"based":[105,112],"on":[106,113,153],"classification":[108],"objective,":[109],"other":[111],"ranking":[115],"objective.":[116],"We":[117],"show":[118],"that":[119],"rankingbased":[121],"variant":[122],"gives":[125],"consistent":[126],"estimates":[128],"under":[129],"weaker":[130],"assumptions":[131],"than":[132],"classification-based":[134,145],"method;":[135],"statistical":[139],"efficiency":[140],"ranking-based":[143],"NCE;":[148],"finally":[149],"describe":[151],"experiments":[152],"synthetic":[154],"data":[155],"language":[157],"modeling":[158],"showing":[159],"effectiveness":[161],"trade-offs":[163],"both":[165],"methods.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}