{"id":"https://openalex.org/W28418033","doi":null,"title":"The unsupervised learning of natural language structure","display_name":"The unsupervised learning of natural language structure","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W28418033","mag":"28418033"},"language":"en","primary_location":{"id":"mag:28418033","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=1087820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","indexed_in":[],"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/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X","observed_orcids":["https://orcid.org/0000-0001-6155-649X"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher D. Manning","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004921249","display_name":"Dan Klein","orcid":"https://orcid.org/0000-0002-8881-1902","observed_orcids":["https://orcid.org/0000-0002-8881-1902","https://orcid.org/0009-0002-5983-2904"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Klein","raw_affiliation_strings":["Stanford University"],"raw_orcid":"https://orcid.org/0000-0002-8881-1902","affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":10.8743,"has_fulltext":true,"cited_by_count":127,"citation_normalized_percentile":{"value":0.98281138,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.00019999999494757503,"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/unsupervised-grammar-induction","display_name":"unsupervised grammar induction","score":0.8899999856948853},{"id":"https://openalex.org/keywords/unsupervised-parsing","display_name":"unsupervised parsing","score":0.8050000071525574},{"id":"https://openalex.org/keywords/dependency-parsing","display_name":"dependency parsing","score":0.6859999895095825},{"id":"https://openalex.org/keywords/multilingual-parsing","display_name":"multilingual parsing","score":0.47600001096725464},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.8899999856948853},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.9319999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788813591003418},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7409365773200989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6836447715759277},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6834203004837036},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5516334176063538},{"id":"https://openalex.org/C70777604","wikidata":"https://www.wikidata.org/wiki/Q257885","display_name":"Word order","level":2,"score":0.47562435269355774},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4276805520057678},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.42677041888237},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4252147674560547},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26131510734558105},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:28418033","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=1087820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W85505375","https://openalex.org/W1495446613","https://openalex.org/W1514872638","https://openalex.org/W1535015163","https://openalex.org/W1572739059","https://openalex.org/W1575798196","https://openalex.org/W1612003148","https://openalex.org/W1632114991","https://openalex.org/W1633960017","https://openalex.org/W1974881914","https://openalex.org/W1978470410","https://openalex.org/W1991865342","https://openalex.org/W1993750641","https://openalex.org/W2019413183","https://openalex.org/W2024657257","https://openalex.org/W2029943890","https://openalex.org/W2047706513","https://openalex.org/W2050423830","https://openalex.org/W2087099129","https://openalex.org/W2089951031","https://openalex.org/W2092654472","https://openalex.org/W2101196694","https://openalex.org/W2110190189","https://openalex.org/W2112861996","https://openalex.org/W2115867364","https://openalex.org/W2123893795","https://openalex.org/W2127314673","https://openalex.org/W2129882630","https://openalex.org/W2139090905","https://openalex.org/W2142708806","https://openalex.org/W2149830985","https://openalex.org/W2149902104","https://openalex.org/W2152496361","https://openalex.org/W2152810530","https://openalex.org/W2153208746","https://openalex.org/W2158997610","https://openalex.org/W2161204834","https://openalex.org/W2163514362","https://openalex.org/W2167072947","https://openalex.org/W2169570971","https://openalex.org/W2170206653","https://openalex.org/W2170716495","https://openalex.org/W2172306595","https://openalex.org/W2294835092","https://openalex.org/W2425667873","https://openalex.org/W2768372964","https://openalex.org/W2888882506","https://openalex.org/W3021713638"],"related_works":["https://openalex.org/W2153568660","https://openalex.org/W7099286888","https://openalex.org/W1554648294","https://openalex.org/W7099138661","https://openalex.org/W2905102582","https://openalex.org/W2102366626","https://openalex.org/W2965013899","https://openalex.org/W1527783480","https://openalex.org/W7099305962","https://openalex.org/W2164910554"],"abstract_inverted_index":{"There":[0],"is":[1,15,56],"precisely":[2],"one":[3],"complete":[4],"language":[5,29,42,142,171],"processing":[6,43],"system":[7],"to":[8,41,59,136,164,308],"date:":[9],"the":[10,36,69,94,112,166,300,316,327],"human":[11,22,328],"brain.":[12],"Though":[13],"there":[14],"debate":[16],"on":[17,49],"how":[18],"much":[19],"built-in":[20],"bias":[21],"learners":[23],"might":[24],"have,":[25],"we":[26,152,178,190,201],"definitely":[27],"acquire":[28],"in":[30,93,209,231,247,250,302,326],"a":[31,81,89,180,192,266],"primarily":[32],"unsupervised":[33,60,248,288],"fashion.":[34],"On":[35],"other":[37],"hand,":[38],"computational":[39],"approaches":[40,61],"are":[44,119,162,258,305,321,323],"almost":[45],"exclusively":[46],"supervised,":[47],"relying":[48],"hand-labeled":[50],"corpora":[51,262],"for":[52,86,104,264,293],"training.":[53],"This":[54],"reliance":[55],"largely":[57],"due":[58],"having":[62],"repeatedly":[63],"exhibited":[64],"discouraging":[65],"performance.":[66],"In":[67],"particular,":[68],"problem":[70],"of":[71,84,96,111,141,169,252,269,318,330],"learning":[72],"syntax":[73,172],"(grammar)":[74],"from":[75,223],"completely":[76],"unannotated":[77],"text":[78],"has":[79],"received":[80],"great":[82],"deal":[83],"attention":[85],"well":[87],"over":[88],"decade,":[90],"with":[91,227,237],"little":[92,225],"way":[95],"positive":[97],"results.":[98],"We":[99],"argue":[100],"that":[101,203],"previous":[102],"methods":[103,257,289],"this":[105,150,303],"task":[106],"have":[107],"generally":[108],"underperformed":[109],"because":[110],"representations":[113,156],"they":[114,212],"used.":[115],"Overly":[116],"complex":[117],"models":[118,132,160,206,301],"easily":[120],"distracted":[121],"by":[122],"non-syntactic":[123],"correlations":[124],"(such":[125,143],"as":[126,144,173,175,278],"topical":[127],"associations),":[128],"while":[129,299],"overly":[130],"simple":[131],"aren't":[133],"rich":[134],"enough":[135],"capture":[137,165],"important":[138],"first-order":[139],"properties":[140],"directionality,":[145],"adjacency,":[146],"and":[147,157,240,281],"valence).":[148],"\r\nIn":[149],"work,":[151],"describe":[153],"several":[154,232],"syntactic":[155],"associated":[158],"probabilistic":[159],"which":[161,184,195],"designed":[163],"basic":[167],"character":[168],"natural":[170],"directly":[174],"possible.":[176],"First,":[177],"examine":[179,191],"nested,":[181],"distributional":[182],"method":[183],"induces":[185,196],"bracketed":[186],"tree":[187],"structures.":[188,199],"Second,":[189],"dependency":[193,198],"model":[194],"word-to-word":[197],"Finally,":[200,298],"demonstrate":[202],"these":[204,216,253],"two":[205],"perform":[207],"better":[208],"combination":[210],"than":[211],"do":[213],"alone.":[214],"With":[215],"representations,":[217],"high-quality":[218],"analyses":[219],"can":[220,314],"be":[221,309],"learned":[222],"surprisingly":[224],"text,":[226],"no":[228],"labeled":[229],"examples,":[230],"languages":[233,295],"(we":[234],"show":[235,244],"experiments":[236],"English,":[238],"German,":[239],"Chinese).":[241],"Our":[242],"results":[243],"above-baseline":[245],"performance":[246],"parsing":[249],"each":[251],"languages.":[254,270],"\r\nGrammar":[255],"induction":[256],"useful":[259],"since":[260],"parsed":[261],"exist":[263],"only":[265],"small":[267],"number":[268],"More":[271],"generally,":[272],"most":[273],"high-level":[274],"NLP":[275],"tasks,":[276],"such":[277],"machine":[279],"translation":[280],"question-answering,":[282],"lack":[283],"richly":[284],"annotated":[285],"corpora,":[286],"making":[287],"extremely":[290],"appealing":[291],"even":[292],"common":[294],"like":[296],"English.":[297],"work":[304],"not":[306,324],"intended":[307],"cognitively":[310],"plausible,":[311],"their":[312],"effectiveness":[313],"inform":[315],"investigation":[317],"what":[319],"biases":[320],"or":[322],"needed":[325],"acquisition":[329],"language.":[331]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":11}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}