{"id":"https://openalex.org/W2295800168","doi":"https://doi.org/10.3115/v1/n15-1027","title":"When and why are log-linear models self-normalizing?","display_name":"When and why are log-linear models self-normalizing?","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2295800168","doi":"https://doi.org/10.3115/v1/n15-1027","mag":"2295800168"},"language":"en","primary_location":{"id":"doi:10.3115/v1/n15-1027","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/n15-1027","pdf_url":"https://doi.org/10.3115/v1/n15-1027","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/n15-1027","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070829652","display_name":"Jacob Andreas","orcid":"https://orcid.org/0000-0002-3141-5845"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jacob Andreas","raw_affiliation_strings":["University of California\u2013Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004921249","display_name":"Dan Klein","orcid":"https://orcid.org/0000-0002-8881-1902"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Klein","raw_affiliation_strings":["University of California\u2013Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070829652"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":12.0175,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.98521391,"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":"244","last_page":"249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9994000196456909,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9994000196456909,"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/T10320","display_name":"Neural Networks and Applications","score":0.9987000226974487,"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/T10057","display_name":"Face and Expression Recognition","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/normalization","display_name":"Normalization (sociology)","score":0.8629610538482666},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7164919972419739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6660499572753906},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5490076541900635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4748111963272095},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4488372206687927},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4315072298049927},{"id":"https://openalex.org/keywords/linear-model","display_name":"Linear model","score":0.42820537090301514},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.41929566860198975},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33941715955734253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3228530287742615},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.32031989097595215},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10475549101829529}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8629610538482666},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7164919972419739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6660499572753906},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5490076541900635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4748111963272095},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4488372206687927},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4315072298049927},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.42820537090301514},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.41929566860198975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33941715955734253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3228530287742615},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32031989097595215},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10475549101829529},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/n15-1027","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/n15-1027","pdf_url":"https://doi.org/10.3115/v1/n15-1027","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.8277","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.8277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/%7Ejda/papers/ak_self_normalizing.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/n15-1027","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/n15-1027","pdf_url":"https://doi.org/10.3115/v1/n15-1027","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2295800168.pdf","grobid_xml":"https://content.openalex.org/works/W2295800168.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W100623710","https://openalex.org/W932413789","https://openalex.org/W1542886316","https://openalex.org/W1590952807","https://openalex.org/W2005708641","https://openalex.org/W2146502635","https://openalex.org/W2152790380","https://openalex.org/W2251682575","https://openalex.org/W2296014541"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W1617617605","https://openalex.org/W4254674344"],"abstract_inverted_index":{"Several":[0],"techniques":[1],"have":[2,39],"recently":[3],"been":[4,41],"pro-posed":[5],"for":[6,18,70,90,100],"training":[7,91,102,106],"\u201cself-normalized":[8],"\u201d":[9],"discrimi-native":[10],"models.":[11,93],"These":[12],"attempt":[13],"to":[14,54],"find":[15],"parameter":[16],"settings":[17],"which":[19,49],"unnormalized":[20],"model":[21,117],"scores":[22],"approximate":[23],"the":[24,29,46],"true":[25],"label":[26],"probability.":[27],"How-ever,":[28],"theoretical":[30],"properties":[31],"of":[32,36,61,86,113],"such":[33],"tech-niques":[34],"(and":[35],"self-normalization":[37,53],"generally)":[38],"not":[40],"investigated.":[42],"This":[43],"paper":[44],"exam-ines":[45],"conditions":[47],"under":[48],"we":[50,81],"can":[51],"ex-pect":[52],"work.":[55],"We":[56],"character-ize":[57],"a":[58,83],"general":[59],"class":[60],"distributions":[62],"that":[63,72],"admit":[64],"self-normalization,":[65],"and":[66,104],"prove":[67],"generalization":[68],"bounds":[69],"procedures":[71],"minimize":[73],"empiri-cal":[74],"normalizer":[75],"variance.":[76],"Motivated":[77],"by":[78,108],"these":[79],"results,":[80],"describe":[82],"novel":[84],"variant":[85],"an":[87],"estab-lished":[88],"procedure":[89,96],"self-normalized":[92],"The":[94],"new":[95],"avoids":[97],"computing":[98],"normalizers":[99],"most":[101],"examples,":[103],"decreases":[105],"time":[107],"as":[109,111],"much":[110],"factor":[112],"ten":[114],"while":[115],"preserving":[116],"quality.":[118],"1":[119]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}