{"id":"https://openalex.org/W2164746297","doi":"https://doi.org/10.3115/v1/p14-2123","title":"EM Decipherment for Large Vocabularies","display_name":"EM Decipherment for Large Vocabularies","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2164746297","doi":"https://doi.org/10.3115/v1/p14-2123","mag":"2164746297"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-2123","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2123","pdf_url":"https://aclanthology.org/P14-2123.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/P14-2123.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103605517","display_name":"Malte Nuhn","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Malte Nuhn","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":1.4474,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84701976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"759","last_page":"764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9940999746322632,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9923999905586243,"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/decipherment","display_name":"Decipherment","score":0.9727102518081665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6834747791290283},{"id":"https://openalex.org/keywords/successor-cardinal","display_name":"Successor cardinal","score":0.6799333691596985},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6495351791381836},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5784251689910889},{"id":"https://openalex.org/keywords/plaintext","display_name":"Plaintext","score":0.4578394591808319},{"id":"https://openalex.org/keywords/cipher","display_name":"Cipher","score":0.42589715123176575},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4242573082447052},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.403602659702301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38785016536712646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3369855284690857},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22798088192939758},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22581732273101807},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10759973526000977},{"id":"https://openalex.org/keywords/encryption","display_name":"Encryption","score":0.10749921202659607}],"concepts":[{"id":"https://openalex.org/C2778467380","wikidata":"https://www.wikidata.org/wiki/Q1345443","display_name":"Decipherment","level":2,"score":0.9727102518081665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6834747791290283},{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.6799333691596985},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6495351791381836},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5784251689910889},{"id":"https://openalex.org/C92717368","wikidata":"https://www.wikidata.org/wiki/Q1162538","display_name":"Plaintext","level":3,"score":0.4578394591808319},{"id":"https://openalex.org/C2780221543","wikidata":"https://www.wikidata.org/wiki/Q4681865","display_name":"Cipher","level":3,"score":0.42589715123176575},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4242573082447052},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.403602659702301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38785016536712646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3369855284690857},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22798088192939758},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22581732273101807},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10759973526000977},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.10749921202659607},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/p14-2123","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2123","pdf_url":"https://aclanthology.org/P14-2123.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.656.5865","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.656.5865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/P/P14/P14-2123.pdf","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:674765","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-211050%22","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Red Hook, NY : Curran 759-764 (2014).","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3115/v1/p14-2123","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2123","pdf_url":"https://aclanthology.org/P14-2123.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2164746297.pdf","grobid_xml":"https://content.openalex.org/works/W2164746297.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W222076935","https://openalex.org/W635530177","https://openalex.org/W1538023239","https://openalex.org/W2013196554","https://openalex.org/W2049633694","https://openalex.org/W2099960657","https://openalex.org/W2102028293","https://openalex.org/W2107791851","https://openalex.org/W2121745180","https://openalex.org/W2123595463","https://openalex.org/W2136346830","https://openalex.org/W2169360026","https://openalex.org/W2172267041"],"related_works":["https://openalex.org/W1991849747","https://openalex.org/W2172267041","https://openalex.org/W2010494859","https://openalex.org/W3200867506","https://openalex.org/W1841707544","https://openalex.org/W3190354679","https://openalex.org/W2917292502","https://openalex.org/W4387233761","https://openalex.org/W4391235179","https://openalex.org/W3035713776"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,45,50,103,124,130],"problem":[4],"of":[5,78,100,113,147],"EMbased":[6],"decipherment":[7,12],"for":[8,110,137],"large":[9],"vocabularies.":[10],"Here,":[11],"is":[13,21,59,90,108,117],"essentially":[14],"a":[15,38,76,97],"tagging":[16,30],"problem:":[17],"Every":[18],"cipher":[19],"token":[20],"tagged":[22],"with":[23,28,63],"some":[24],"plaintext":[25],"type.":[26],"As":[27],"other":[29],"problems,":[31],"this":[32,64,142],"one":[33],"can":[34],"be":[35],"treated":[36],"as":[37],"Hidden":[39],"Markov":[40],"Model":[41],"(HMM),":[42],"only":[43,95],"here,":[44],"vocabularies":[46],"are":[47,134],"large,":[48],"so":[49],"usual":[51],"O(N":[52],"V":[53],"2":[54],")":[55],"exact":[56],"EM":[57,80],"approach":[58],"infeasible.":[60],"When":[61],"faced":[62],"situation,":[65],"many":[66],"people":[67],"turn":[68],"to":[69,74,91,118,122],"sampling.":[70],"However,":[71],"we":[72],"propose":[73],"use":[75,119],"type":[77],"approximate":[79],"and":[81,150],"show":[82],"that":[83,133],"it":[84],"works":[85],"well.":[86],"The":[87,106,126],"basic":[88],"idea":[89],"collect":[92],"fractional":[93],"counts":[94],"over":[96],"small":[98],"subset":[99,107],"links":[101],"in":[102],"forward-backward":[104],"lattice.":[105],"different":[109],"each":[111,138],"iteration":[112],"EM.":[114],"One":[115],"option":[116],"beam":[120],"search":[121],"do":[123],"subsetting.":[125],"second":[127],"method":[128],"restricts":[129],"successor":[131],"words":[132],"looked":[135],"at,":[136],"hypothesis.":[139],"It":[140],"does":[141],"by":[143],"consulting":[144],"pre-computed":[145],"tables":[146],"likely":[148,151],"n-grams":[149],"substitutions.":[152]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}