{"id":"https://openalex.org/W1495096912","doi":"https://doi.org/10.1109/icassp.2015.7178967","title":"Improving n-gram probability estimates by compound-head clustering","display_name":"Improving n-gram probability estimates by compound-head clustering","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1495096912","doi":"https://doi.org/10.1109/icassp.2015.7178967","mag":"1495096912"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/bitstream/123456789/484789/1/3849_postprint.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071928196","display_name":"Joris Pelemans","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Joris Pelemans","raw_affiliation_strings":["Dept. ESAT, Katholieke Universiteit, Leuven, Belgium","[Dept. ESAT, Katholieke Universiteit Leuven, Belgium]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. ESAT, Katholieke Universiteit, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"[Dept. ESAT, Katholieke Universiteit Leuven, Belgium]","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046536366","display_name":"Kris Demuynck","orcid":"https://orcid.org/0000-0001-8525-7160"},"institutions":[{"id":"https://openalex.org/I2801831186","display_name":"Elia (Belgium)","ror":"https://ror.org/00227f603","country_code":"BE","type":"company","lineage":["https://openalex.org/I2801831186"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kris Demuynck","raw_affiliation_strings":["ELIS Ghent University, Belgium","ELIS, Ghent Univ., Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELIS Ghent University, Belgium","institution_ids":["https://openalex.org/I2801831186"]},{"raw_affiliation_string":"ELIS, Ghent Univ., Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van hamme","raw_affiliation_strings":["Katholieke Universiteit Leuven, Leuven, Flanders, BE","[Dept. ESAT, Katholieke Universiteit Leuven, Belgium]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Katholieke Universiteit Leuven, Leuven, Flanders, BE","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"[Dept. ESAT, Katholieke Universiteit Leuven, Belgium]","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030624808","display_name":"Patrick Wambacq","orcid":"https://orcid.org/0000-0002-9284-3069"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Patrick Wambacq","raw_affiliation_strings":["Dept. ESAT, Katholieke Universiteit, Leuven, Belgium","[Dept. ESAT, Katholieke Universiteit Leuven, Belgium]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. ESAT, Katholieke Universiteit, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"[Dept. ESAT, Katholieke Universiteit Leuven, Belgium]","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4452,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75544268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"i","issue":null,"first_page":"5221","last_page":"5225"},"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":0.9995999932289124,"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":0.9986000061035156,"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/cluster-analysis","display_name":"Cluster analysis","score":0.650367021560669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.594979465007782},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5294551253318787},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.4874325096607208},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4721284806728363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29165583848953247},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08439135551452637}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.650367021560669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.594979465007782},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5294551253318787},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.4874325096607208},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4721284806728363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29165583848953247},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08439135551452637},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2015.7178967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/484789","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/484789/3/3849_final.pdf","pdf_url":"https://lirias.kuleuven.be/bitstream/123456789/484789/1/3849_postprint.pdf","source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE international conference on acoustics, speech, and signal processing - ICASSP\u20192015, Brisbane, Australia, 19-24 April 2015","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:archive.ugent.be:7227973","is_oa":false,"landing_page_url":"https://biblio.ugent.be/publication/7227973","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1520-6149","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/484789","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/484789/3/3849_final.pdf","pdf_url":"https://lirias.kuleuven.be/bitstream/123456789/484789/1/3849_postprint.pdf","source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE international conference on acoustics, speech, and signal processing - ICASSP\u20192015, Brisbane, Australia, 19-24 April 2015","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1495096912.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W179875071","https://openalex.org/W1269315465","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1934041838","https://openalex.org/W2027637429","https://openalex.org/W2082092506","https://openalex.org/W2113641473","https://openalex.org/W2121227244","https://openalex.org/W2134454005","https://openalex.org/W2147152072","https://openalex.org/W2151111414","https://openalex.org/W2153330999","https://openalex.org/W2158195707","https://openalex.org/W2168664213","https://openalex.org/W2396189684","https://openalex.org/W2401165322","https://openalex.org/W2403552175","https://openalex.org/W6601546654","https://openalex.org/W6628009067","https://openalex.org/W6636440780","https://openalex.org/W6639619044","https://openalex.org/W6674504384","https://openalex.org/W6678277124","https://openalex.org/W6684361878","https://openalex.org/W6712179664","https://openalex.org/W6712951788"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2625039379","https://openalex.org/W2088254117","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W1901380241","https://openalex.org/W311963822","https://openalex.org/W2789473152","https://openalex.org/W3132255358"],"abstract_inverted_index":{"Compounding":[0],"is":[1,14,58,133],"one":[2],"of":[3,19,35,93,120,135],"the":[4,38,97,121],"most":[5,34],"productive":[6],"word":[7,154],"formation":[8],"processes":[9],"in":[10,22],"many":[11],"languages":[12],"and":[13,43,60,125],"therefore":[15],"a":[16,45,63,84,90,143,152],"main":[17],"source":[18],"data":[20],"sparsity":[21],"language":[23,122,147],"modeling.":[24],"Many":[25],"solutions":[26],"have":[27],"been":[28],"suggested":[29],"to":[30,82,151],"model":[31,47,87],"compound":[32,39,70,139],"words,":[33],"which":[36,149],"break":[37],"into":[40],"its":[41],"constituents":[42],"train":[44],"new":[46],"with":[48,73,128],"them.":[49],"In":[50,103],"earlier":[51],"work,":[52],"we":[53,61,106],"argued":[54],"that":[55,66,88],"this":[56,104,109],"approach":[57],"suboptimal":[59],"presented":[62],"novel":[64],"technique":[65,132],"clusters":[67,78],"new,":[68],"domain-specific":[69],"words":[71],"together":[72],"their":[74],"semantic":[75],"heads.":[76],"The":[77],"were":[79],"then":[80],"used":[81],"build":[83],"class-based":[85],"n-gram":[86,94,146],"enabled":[89],"reliable":[91],"estimation":[92],"probabilities,":[95],"without":[96],"need":[98],"for":[99,158],"additional":[100],"training":[101],"data.":[102],"paper,":[105],"investigate":[107],"how":[108],"\u201csemantic":[110],"head":[111],"mapping\u201d":[112],"can":[113],"best":[114],"be":[115],"made":[116],"an":[117],"integral":[118],"part":[119],"modeling":[123],"strategy":[124],"find":[126],"that,":[127],"some":[129],"adaptations,":[130],"our":[131],"capable":[134],"producing":[136],"more":[137],"accurate":[138],"probability":[140],"estimates":[141],"than":[142],"baseline":[144],"word-based":[145],"model,":[148],"lead":[150],"significant":[153],"error":[155],"rate":[156],"reduction":[157],"Dutch":[159],"read":[160],"speech.":[161]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
