{"id":"https://openalex.org/W2027637429","doi":"https://doi.org/10.1109/icassp.2014.6853574","title":"Coping with language data sparsity: Semantic head mapping of compound words","display_name":"Coping with language data sparsity: Semantic head mapping of compound words","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2027637429","doi":"https://doi.org/10.1109/icassp.2014.6853574","mag":"2027637429"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/handle/123456789/450751","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 Univ. Leuven, 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 Univ. Leuven, 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/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":["DSSP, Ghent University, Belgium","DSSP, Ghent Univ., Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DSSP, Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"DSSP, Ghent Univ., Ghent, 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":["Dept. ESAT, Katholieke Universiteit Leuven, Belgium","Dept. ESAT, Katholieke Univ. Leuven, 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 Univ. Leuven, 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 Univ. Leuven, 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 Univ. Leuven, 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":1.6916,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87479418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"141","last_page":"145"},"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":0.9998000264167786,"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":0.9997000098228455,"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/perplexity","display_name":"Perplexity","score":0.7735751867294312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7382513284683228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6902824640274048},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6539444327354431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6153174638748169},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.47054818272590637},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45619019865989685},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4159836769104004},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3681378960609436},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3235473036766052},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14673301577568054},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09256842732429504}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7735751867294312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382513284683228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6902824640274048},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6539444327354431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6153174638748169},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.47054818272590637},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45619019865989685},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4159836769104004},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3681378960609436},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3235473036766052},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14673301577568054},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09256842732429504},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2014.6853574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:4404017","is_oa":false,"landing_page_url":"https://biblio.ugent.be/publication/4404017","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":"ISBN: 9781479928934","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/450751","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/450751","pdf_url":null,"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\u20192014, Florence, Italy, 4-9 May 2014","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/450751","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/450751","pdf_url":null,"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\u20192014, Florence, Italy, 4-9 May 2014","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W15942306","https://openalex.org/W581469913","https://openalex.org/W1269315465","https://openalex.org/W1612003148","https://openalex.org/W1731244441","https://openalex.org/W1880262756","https://openalex.org/W1934041838","https://openalex.org/W1956785191","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/W2158195707","https://openalex.org/W2168664213","https://openalex.org/W2240478310","https://openalex.org/W2401165322","https://openalex.org/W2403552175","https://openalex.org/W4233559841","https://openalex.org/W4237791300","https://openalex.org/W6600665201","https://openalex.org/W6628009067","https://openalex.org/W6636440780","https://openalex.org/W6637672553","https://openalex.org/W6678277124","https://openalex.org/W6684361878","https://openalex.org/W6690391762","https://openalex.org/W6712951788"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2020757772","https://openalex.org/W2902731467"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,59,95,100,112],"novel":[6],"clustering":[7,43],"technique":[8,20,83],"for":[9,27],"compound":[10],"words.":[11],"By":[12],"mapping":[13],"compounds":[14,33,89],"onto":[15],"their":[16,38,91],"semantic":[17,54,92],"heads,":[18],"the":[19,42,49],"is":[21,84],"able":[22],"to":[23],"estimate":[24],"n-gram":[25],"probabilities":[26],"unseen":[28],"compounds.":[29],"We":[30],"argue":[31],"that":[32,81],"are":[34,56],"well":[35],"represented":[36],"by":[37,58],"heads":[39,55,93],"which":[40,62],"allows":[41],"of":[44,51,64,86,97,102],"rare":[45],"words":[46],"and":[47,67,90,99,118],"reduces":[48],"risk":[50],"over-generalization.":[52],"The":[53],"obtained":[57],"two-step":[60],"process":[61],"consists":[63],"constituent":[65],"generation":[66],"best":[68],"head":[69],"selection":[70],"based":[71],"on":[72,76],"corpus":[73],"statistics.":[74],"Experiments":[75],"Dutch":[77],"read":[78],"speech":[79],"show":[80],"our":[82],"capable":[85],"correctly":[87],"identifying":[88],"with":[94,108],"precision":[96],"80.25%":[98],"recall":[101],"85.97%.":[103],"A":[104],"class-based":[105],"language":[106],"model":[107],"compound-head":[109],"clusters":[110],"achieves":[111],"significant":[113],"reduction":[114],"in":[115],"both":[116],"perplexity":[117],"WER.":[119]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}