{"id":"https://openalex.org/W7096912948","doi":null,"title":"Invited Applications Paper Climbing the Tower of Babel: Unsupervised Multilingual Learning","display_name":"Invited Applications Paper Climbing the Tower of Babel: Unsupervised Multilingual Learning","publication_year":2010,"publication_date":"2010-08-30","ids":{"openalex":"https://openalex.org/W7096912948"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.170.1648","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.1648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icml2010.org/papers/905.pdf","raw_type":"text"},"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/A5039445725","display_name":"Benjamin Snyder","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Snyder","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010124873","display_name":"Regina Barzilay","orcid":"https://orcid.org/0000-0002-2921-8201","observed_orcids":["https://orcid.org/0000-0002-2921-8201"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Regina Barzilay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53932685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-language-models","display_name":"probabilistic language models","score":0.7749999761581421},{"id":"https://openalex.org/keywords/language-relations","display_name":"language relations","score":0.32199999690055847},{"id":"https://openalex.org/keywords/morphological-segmentation","display_name":"morphological segmentation","score":0.8709999918937683},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":1.0},{"id":"https://openalex.org/keywords/syntactic-analysis","display_name":"syntactic analysis","score":0.9980000257492065},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9079999923706055},{"id":"https://openalex.org/keywords/linguistic-annotation","display_name":"linguistic annotation","score":0.3070000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7423999905586243},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.7178000211715698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7001000046730042},{"id":"https://openalex.org/C2778467380","wikidata":"https://www.wikidata.org/wiki/Q1345443","display_name":"Decipherment","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38109999895095825},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2777831296","wikidata":"https://www.wikidata.org/wiki/Q12518","display_name":"Tower","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.170.1648","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.1648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icml2010.org/papers/905.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.8495821952819824,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2254954578","https://openalex.org/W2185976226","https://openalex.org/W2116211107","https://openalex.org/W7095700971","https://openalex.org/W3093721400","https://openalex.org/W2141476920","https://openalex.org/W4409178524","https://openalex.org/W6993019404","https://openalex.org/W4406101390","https://openalex.org/W2986195527"],"abstract_inverted_index":{"For":[0,175,191],"centuries,":[1],"scholars":[2],"have":[3,117,166],"explored":[4],"the":[5,66,87,90,98,110,120,125,131,142,156,159,169,193,200,203,231,234],"deep":[6],"links":[7,24],"among":[8],"human":[9],"languages.":[10,71,236],"In":[11],"this":[12,103],"paper,":[13],"we":[14,59],"present":[15,61],"a":[16,26,62,81,213],"class":[17],"of":[18,28,69,89,100,106,127,130,136,144,152,158,161,171,178,215,233],"probabilistic":[19],"models":[20,33],"that":[21,165],"use":[22],"these":[23,55,137,153],"as":[25,46],"form":[27],"naturally":[29],"occurring":[30],"supervision.":[31],"These":[32],"allow":[34],"us":[35],"to":[36,148,189,218,223,227],"substantially":[37],"improve":[38],"performance":[39,170],"for":[40,65,212,230],"core":[41],"text":[42,75],"processing":[43],"tasks,":[44,58],"such":[45,225],"morphological":[47],"segmentation,":[48],"part-of-speech":[49],"tagging,":[50],"and":[51,83,187],"syntactic":[52],"parsing.":[53],"Besides":[54],"traditional":[56],"NLP":[57,114,145],"also":[60],"multilingual":[63],"model":[64],"computational":[67],"decipherment":[68],"lost":[70],"1.":[72],"Overview":[73],"Electronic":[74],"is":[76,154,221],"currently":[77,140],"being":[78],"produced":[79],"at":[80],"vast":[82],"unprecedented":[84],"scale":[85],"across":[86],"languages":[88,129,138],"world.":[91],"Natural":[92],"Language":[93],"Processing":[94],"(NLP)":[95],"holds":[96],"out":[97],"promise":[99],"automatically":[101],"analyzing":[102],"growing":[104],"body":[105],"text.":[107],"However,":[108],"over":[109],"last":[111],"several":[112,149],"decades,":[113],"research":[115],"efforts":[116],"focused":[118],"on":[119],"English":[121,172,201],"language,":[122,202],"often":[123],"neglecting":[124],"thousands":[126],"other":[128],"world":[132],"(Bender,":[133],"2009).":[134],"Most":[135],"are":[139],"beyond":[141],"reach":[143],"technology":[146],"due":[147],"factors.":[150],"One":[151],"simply":[155],"lack":[157],"kinds":[160],"hand-annotated":[162,181],"linguistic":[163,179],"resources":[164,226],"helped":[167],"propel":[168],"language":[173],"systems.":[174],"complex":[176],"tasks":[177],"analysis,":[180],"corpora":[182],"can":[183],"be":[184],"prohibitively":[185],"time-consuming":[186],"expensive":[188],"produce.":[190,219],"example,":[192],"most":[194],"widely":[195],"used":[196],"annotated":[197],"corpus":[198],"in":[199],"Penn":[204],"Treebank":[205],"(Marcus":[206],"et":[207],"al.,":[208],"1994),":[209],"took":[210],"years":[211],"team":[214],"professional":[216],"linguists":[217],"It":[220],"unrealistic":[222],"expect":[224],"ever":[228],"exist":[229],"majority":[232],"world\u2019s":[235]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}