{"id":"https://openalex.org/W163823652","doi":"https://doi.org/10.21437/eurospeech.2003-113","title":"A corpus-based decompounding algorithm for German lexical modeling in LVCSR","display_name":"A corpus-based decompounding algorithm for German lexical modeling in LVCSR","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W163823652","doi":"https://doi.org/10.21437/eurospeech.2003-113","mag":"163823652"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-113","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-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/A5041761844","display_name":"Martine Adda\u2010Decker","orcid":"https://orcid.org/0000-0003-2154-7438"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Martine Adda-Decker","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041761844"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4039,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.83774549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9939000010490417,"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":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.8318908214569092},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.731509268283844},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6880317330360413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5982016921043396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.442261278629303},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24879595637321472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318908214569092},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.731509268283844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6880317330360413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5982016921043396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.442261278629303},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24879595637321472},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-113","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.2443","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.2443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://tlp.limsi.fr/public/ES031038.PDF","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W14754660","https://openalex.org/W112233275","https://openalex.org/W148334237","https://openalex.org/W1506201763","https://openalex.org/W1719940802","https://openalex.org/W2116292667","https://openalex.org/W2338741179"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2315527029","https://openalex.org/W2065387230","https://openalex.org/W2323937687","https://openalex.org/W648995381","https://openalex.org/W3033791384","https://openalex.org/W2141885522","https://openalex.org/W2776312268","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"a":[3,38,64,84],"corpus-based":[4],"decompounding":[5,15],"algorithm":[6,16,34,79,145],"is":[7,35,138],"described":[8],"and":[9,27],"applied":[10,82],"for":[11,23,126],"German":[12,130],"LVCSR.":[13],"The":[14,30,78],"contributes":[17],"to":[18,83,107,118,150],"address":[19],"two":[20],"major":[21],"problems":[22],"LVCSR:":[24],"lexical":[25],"coverage":[26],"letter-to-sound":[28],"conversion.":[29],"idea":[31],"of":[32,41,70,101,105],"the":[33,54,68,127,141,144],"simple:":[36],"given":[37],"word":[39,52,60,66,86,103,114],"start":[40,61],"length":[42],"#":[43,62],"only":[44],"few":[45],"different":[46],"characters":[47,72],"can":[48,73,146],"continue":[49],"an":[50],"admissible":[51],"in":[53],"language.":[55,153],"But":[56],"concerning":[57],"compounds,":[58],"if":[59],"reaches":[63],"constituent":[65],"boundary,":[67],"set":[69],"successor":[71],"theoretically":[74],"include":[75],"any":[76,151],"character.":[77],"has":[80],"been":[81,96,111,124],"300M":[85],"corpus":[87],"with":[88],"2.6M":[89],"distinct":[90],"words.":[91,120],"800k":[92],"decomposition":[93],"rules":[94],"have":[95,110,123],"extracted":[97],"automatically.":[98],"OOV":[99],"(out":[100],"vocabulary)":[102],"reductions":[104],"25%":[106],"50%":[108],"relative":[109],"achieved":[112],"using":[113],"lists":[115],"from":[116],"65k":[117],"600k":[119],"Pronunciation":[121],"dictionaries":[122],"developed":[125],"LIMSI":[128],"300k":[129],"recognition":[131],"system.":[132],"As":[133],"no":[134],"language":[135],"specific":[136],"knowledge":[137],"required":[139],"beyond":[140],"text":[142],"corpus,":[143],"apply":[147],"more":[148],"generally":[149],"compounding":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}