{"id":"https://openalex.org/W21103258","doi":null,"title":"Unsupervised Learning for Natural Language Processing.","display_name":"Unsupervised Learning for Natural Language Processing.","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W21103258","mag":"21103258"},"language":"en","primary_location":{"id":"mag:21103258","doi":null,"is_oa":false,"landing_page_url":"http://colt2008.cs.helsinki.fi/papers/klein.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418075","display_name":"Conference on Learning Theory","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference on Learning Theory","raw_type":null},"volume":null,"type":"conference-paper","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/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/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":"Dan Klein","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":"https://orcid.org/0000-0002-8881-1902","affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004921249"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.00150123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9839000105857849,"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":0.9839000105857849,"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":0.015200000256299973,"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/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-learning","display_name":"unsupervised learning","score":0.9750000238418579},{"id":"https://openalex.org/keywords/latent-variable-modeling","display_name":"latent variable models","score":0.9490000009536743},{"id":"https://openalex.org/keywords/syntactic-analysis","display_name":"syntactic analysis","score":0.8169999718666077},{"id":"https://openalex.org/keywords/grammatical-inference","display_name":"grammatical inference","score":0.9940000176429749},{"id":"https://openalex.org/keywords/coreference-resolution","display_name":"coreference resolution","score":0.8489999771118164},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"hierarchical Dirichlet process","score":0.9750000238418579},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.6899999976158142},{"id":"https://openalex.org/keywords/non-parallel-corpora","display_name":"non-parallel corpora","score":0.8429999947547913},{"id":"https://openalex.org/keywords/word-alignment","display_name":"word alignment","score":0.5879999995231628},{"id":"https://openalex.org/keywords/attentional-state","display_name":"attentional state","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657867908477783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7720756530761719},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.707627534866333},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5910738110542297},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.5874384045600891},{"id":"https://openalex.org/C56601403","wikidata":"https://www.wikidata.org/wiki/Q5593673","display_name":"Grammar induction","level":3,"score":0.5159562230110168},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4468223452568054},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.4297630786895752},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.21231001615524292}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:21103258","doi":null,"is_oa":false,"landing_page_url":"http://colt2008.cs.helsinki.fi/papers/klein.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418075","display_name":"Conference on Learning Theory","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference on Learning Theory","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.8299999833106995}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W573534493","https://openalex.org/W6978991728"],"related_works":["https://openalex.org/W28418033","https://openalex.org/W2133330531","https://openalex.org/W2133924262","https://openalex.org/W1612381393","https://openalex.org/W2137116301","https://openalex.org/W2566475580","https://openalex.org/W2153568660","https://openalex.org/W73497385","https://openalex.org/W2250941477","https://openalex.org/W2293259138"],"abstract_inverted_index":{"Given":[0,156],"the":[1,68,126,182],"abundance":[2],"of":[3,75,111,176],"text":[4],"data,":[5],"unsupervised":[6,54],"approaches":[7],"are":[8,88,101,149,187],"very":[9],"appealing":[10],"for":[11,131],"natural":[12],"language":[13],"processing.":[14],"We":[15],"present":[16,135],"three":[17],"latent":[18],"variable":[19],"systems":[20],"which":[21,42,86,138],"achieve":[22],"state-of-the-art":[23],"results":[24,71],"in":[25,52,72,85],"domains":[26],"previously":[27],"dominated":[28],"by":[29,107,151],"fully":[30,119],"supervised":[31,128],"systems.":[32],"For":[33,77],"syntactic":[34,46],"parsing,":[35],"we":[36,80,134],"describe":[37,81],"a":[38,73,82,93,108,136,152,160],"grammar":[39],"induction":[40],"technique":[41],"begins":[43],"with":[44,125],"coarse":[45],"structures":[47],"and":[48,65,114,185],"iteratively":[49],"refines":[50],"them":[51],"an":[53],"fashion.":[55],"The":[56],"resulting":[57],"coarse-to-fine":[58,62],"grammars":[59],"admit":[60],"efficient":[61],"inference":[63],"schemes":[64],"have":[66],"produced":[67],"best":[69,127],"parsing":[70],"variety":[74],"languages.":[76],"coreference":[78],"resolution,":[79],"discourse":[83],"model":[84,110,137],"entities":[87,100],"shared":[89],"across":[90],"documents":[91],"using":[92],"hierarchical":[94],"Dirichlet":[95],"process.":[96],"In":[97],"each":[98],"document,":[99],"repeatedly":[102],"rendered":[103],"into":[104],"mention":[105],"strings":[106],"sequential":[109],"attentional":[112],"state":[113],"anaphoric":[115],"constraint.":[116],"Despite":[117],"being":[118],"unsupervised,":[120],"this":[121],"approach":[122,173],"is":[123,174],"competitive":[124],"approaches.":[129],"Finally,":[130],"machine":[132],"translation,":[133],"learns":[139],"translation":[140],"lexicons":[141],"from":[142,167],"non-parallel":[143],"corpora.":[144],"Alignments":[145],"between":[146],"word":[147,164],"types":[148],"modeled":[150],"prior":[153],"over":[154,163],"matchings.":[155],"any":[157],"fixed":[158],"alignment,":[159],"joint":[161],"density":[162],"vectors":[165],"derives":[166],"probabilistic":[168],"canonical":[169],"correlation":[170],"analysis.":[171],"This":[172],"capable":[175],"discovering":[177],"high-precision":[178],"translations,":[179],"even":[180],"when":[181],"underlying":[183],"corpora":[184],"languages":[186],"divergent.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-09-24T07:57:37.273135","created_date":"2016-06-24T00:00:00"}