{"id":"https://openalex.org/W2094828966","doi":"https://doi.org/10.1080/09296170600850700","title":"A dynamic context shortening method for a minimum-context grapheme-to-phoneme data-driven transducer generator","display_name":"A dynamic context shortening method for a minimum-context grapheme-to-phoneme data-driven transducer generator","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2094828966","doi":"https://doi.org/10.1080/09296170600850700","mag":"2094828966"},"language":"en","primary_location":{"id":"doi:10.1080/09296170600850700","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09296170600850700","pdf_url":null,"source":{"id":"https://openalex.org/S24321443","display_name":"Journal of Quantitative Linguistics","issn_l":"0929-6174","issn":["0929-6174","1744-5035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847"],"host_organization_lineage_names":["Routledge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Quantitative Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5000708505","display_name":"Andrzej Pluci\u0144ski","orcid":null},"institutions":[{"id":"https://openalex.org/I59411706","display_name":"Adam Mickiewicz University in Pozna\u0144","ror":"https://ror.org/04g6bbq64","country_code":"PL","type":"education","lineage":["https://openalex.org/I59411706"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Andrzej Pluci\u0144ski","raw_affiliation_strings":["Instytut J\u0119zykoznawstwa, Uniwersytet im. A. Mickiewicza"],"affiliations":[{"raw_affiliation_string":"Instytut J\u0119zykoznawstwa, Uniwersytet im. A. Mickiewicza","institution_ids":["https://openalex.org/I59411706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000708505"],"corresponding_institution_ids":["https://openalex.org/I59411706"],"apc_list":null,"apc_paid":null,"fwci":0.4517,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73740767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"2-3","first_page":"195","last_page":"223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9969000220298767,"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":0.9706000089645386,"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/grapheme","display_name":"Grapheme","score":0.7524603009223938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7286453247070312},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.7144302129745483},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6542119979858398},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.5582190155982971},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5412665009498596},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5180109143257141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46633267402648926},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41514915227890015},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25528040528297424},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07736283540725708}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.7524603009223938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286453247070312},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7144302129745483},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6542119979858398},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.5582190155982971},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5412665009498596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5180109143257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46633267402648926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41514915227890015},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25528040528297424},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07736283540725708},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/09296170600850700","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09296170600850700","pdf_url":null,"source":{"id":"https://openalex.org/S24321443","display_name":"Journal of Quantitative Linguistics","issn_l":"0929-6174","issn":["0929-6174","1744-5035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847"],"host_organization_lineage_names":["Routledge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Quantitative Linguistics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W110726504","https://openalex.org/W155281255","https://openalex.org/W1510007267","https://openalex.org/W1514949327","https://openalex.org/W1579953115","https://openalex.org/W1580142630","https://openalex.org/W1581253957","https://openalex.org/W1644623430","https://openalex.org/W1704572586","https://openalex.org/W2007353992","https://openalex.org/W2020190016","https://openalex.org/W2025098865","https://openalex.org/W2038466182","https://openalex.org/W2069828345","https://openalex.org/W2116474332","https://openalex.org/W2129407130","https://openalex.org/W2148081319","https://openalex.org/W2148756486","https://openalex.org/W2154341695","https://openalex.org/W2315348142","https://openalex.org/W2324077940","https://openalex.org/W2396764420","https://openalex.org/W2397961719","https://openalex.org/W2603454388","https://openalex.org/W2609724207"],"related_works":["https://openalex.org/W2621258238","https://openalex.org/W2132470403","https://openalex.org/W2745284343","https://openalex.org/W2155576284","https://openalex.org/W2795856091","https://openalex.org/W2161573742","https://openalex.org/W2462492290","https://openalex.org/W2008308193","https://openalex.org/W3037190132","https://openalex.org/W2028097510"],"abstract_inverted_index":{"We":[0,82],"present":[1],"an":[2],"efficient":[3],"way":[4],"to":[5,29,93,208,215,242],"learn":[6,216],"automatically":[7],"letter-to-phoneme":[8],"mapping":[9],"rules":[10,26,230],"for":[11,40,55,164,199],"Polish":[12,174,217],"by":[13],"using":[14],"the":[15,44,74,78,88,112,117,123,138,155,158,161,259],"concept":[16],"of":[17,24,77,140,157,173,247,251,261,264],"\u201cdynamic":[18],"context":[19,90,99,125],"shortening":[20],"method\u201d.Attempts":[21],"at":[22,135,190],"reconstruction":[23],"transcription":[25,75,96,162],"date":[27],"back":[28],"1987,":[30],"when":[31],"Sejnowski":[32],"and":[33,66,106,129,152,182,192,234],"Rosenberg":[34],"applied":[35,244,256],"a":[36,210,235,248,252],"self-organizing":[37],"neural":[38],"network":[39],"\u201cgrapheme-to-phoneme\u201d":[41],"mapping.":[42],"In":[43,115],"latter":[45],"approaches":[46],"decision":[47],"tree":[48],"based":[49],"methods":[50,226,255],"were":[51,58,69,108,127,130,167,186,197],"applied.":[52],"The":[53,64,194,238,254],"trees":[54],"each":[56,165],"letter":[57,166],"built":[59],"starting":[60],"from":[61,87,188],"empty":[62],"contexts.":[63],"left":[65,105,145],"right":[67,147],"contexts":[68],"then":[70],"alternately":[71,110],"widened":[72],"until":[73,111],"ambiguity":[76,113],"training":[79,184,213],"data":[80],"disappeared.":[81],"started":[83],"in":[84,97,245],"our":[85],"approach":[86],"symmetrical":[89],"wide":[91],"enough":[92,207],"ensure":[94],"unambiguous":[95],"every":[98,136],"surroundings.":[100],"Then":[101],"both":[102],"contexts,":[103],"i.e.,":[104],"right,":[107],"shortened":[109,132],"appeared.":[114],"all":[116],"cases":[118],"where":[119],"ambiguous":[120],"transcriptions":[121],"occurred,":[122],"previous":[124],"forms":[126],"restored":[128],"not":[131],"further.":[133],"Therefore":[134],"step":[137],"cause":[139],"ambiguity,":[141],"namely":[142],"too":[143],"short":[144],"or":[146],"context,":[148],"was":[149,180,206,240],"clearly":[150],"known":[151],"removed.":[153],"On":[154],"basis":[156],"results":[159],"obtained,":[160],"tables":[163],"constructed.":[168],"A":[169],"350,000":[170],"character":[171,212],"corpus":[172],"text":[175],"transcribed":[176],"into":[177],"phonemic":[178],"form":[179],"prepared":[181],"different-length":[183],"samples":[185],"taken":[187],"it":[189,205],"random":[191],"analysed.":[193],"remaining":[195],"parts":[196],"used":[198],"verification.":[200],"It":[201],"turned":[202],"out":[203],"that":[204],"prepare":[209],"30,000":[211],"sample":[214],"grapheme-to-phoneme":[218],"minimum-context":[219],"mapping.We":[220],"describe":[221],"also":[222],"three":[223],"original":[224],"generalization":[225],"which":[227],"we":[228],"call":[229],"coring,":[231],"indeterminacies":[232],"absorption":[233],"guessing":[236],"method.":[237],"last":[239],"invented":[241],"be":[243],"case":[246],"limited":[249],"acceptance":[250],"context.":[253],"together":[257],"allow":[258],"removal":[260],"about":[262],"70%":[263],"errors.":[265]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}