{"id":"https://openalex.org/W43096115","doi":"https://doi.org/10.21437/eurospeech.2001-216","title":"Smoothing issues in the structured language model","display_name":"Smoothing issues in the structured language model","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W43096115","doi":"https://doi.org/10.21437/eurospeech.2001-216","mag":"43096115"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-216","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5101679885","display_name":"Woosung Kim","orcid":"https://orcid.org/0000-0001-7139-5968"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Woosung Kim","raw_affiliation_strings":["Johns Hopkins University ("],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University ("],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072718837","display_name":"Wu Jun","orcid":"https://orcid.org/0000-0001-6879-620X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Wu","raw_affiliation_strings":["Johns Hopkins University ("],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101679885"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.1805,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88462715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"717","last_page":"720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/T13629","display_name":"Text Readability and Simplification","score":0.9948999881744385,"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":0.8367229700088501},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.8139904141426086},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7037373781204224},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6821024417877197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6195676922798157},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6156523823738098},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5848612785339355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5420050024986267},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5138599872589111},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4857223629951477},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.48344215750694275},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.48062223196029663},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4322279095649719},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.4131615161895752},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24425897002220154},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0826776921749115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367229700088501},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8139904141426086},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7037373781204224},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6821024417877197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6195676922798157},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6156523823738098},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5848612785339355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5420050024986267},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5138599872589111},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4857223629951477},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.48344215750694275},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.48062223196029663},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4322279095649719},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.4131615161895752},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24425897002220154},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0826776921749115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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":2,"locations":[{"id":"doi:10.21437/eurospeech.2001-216","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.9150","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.9150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.jhu.edu/~junwu/eurospeech01.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1497026191","https://openalex.org/W1632114991","https://openalex.org/W1934041838","https://openalex.org/W1989705153","https://openalex.org/W2110882317","https://openalex.org/W2114858359","https://openalex.org/W2158195707","https://openalex.org/W2166637769","https://openalex.org/W2343954916"],"related_works":["https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2787311093","https://openalex.org/W2132221452","https://openalex.org/W2105076537","https://openalex.org/W1577263324","https://openalex.org/W2169518243","https://openalex.org/W2050138804","https://openalex.org/W2151348424","https://openalex.org/W1494910745"],"abstract_inverted_index":{"The":[0],"Structured":[1],"Language":[2],"Model":[3],"(SLM)":[4],"recently":[5],"introduced":[6],"by":[7,94],"Chelba":[8],"and":[9,30,48,91,121,130],"Jelinek":[10],"is":[11,146],"a":[12,21,68],"powerful":[13],"general":[14],"formalism":[15],"for":[16,25,51,58],"exploiting":[17],"syntactic":[18,75],"dependencies":[19,66,87],"in":[20,88,142],"left-to-right":[22],"language":[23],"model":[24],"applications":[26],"such":[27],"as":[28,82],"speech":[29],"handwriting":[31],"recognition,":[32],"spelling":[33],"correction,":[34],"machine":[35],"translation,":[36],"etc.":[37],"Unlike":[38],"traditional":[39],"N-gram":[40,84,99,110],"models,":[41],"optimal":[42],"smoothing":[43],"techniques":[44],"--":[45,53,119,123],"discounting":[46],"methods":[47,133],"hierarchical":[49],"structures":[50],"back-off":[52,128],"are":[54,80],"still":[55],"being":[56],"developed":[57],"the":[59,62,64,89,95,136,139,150],"SLM.":[60,140],"In":[61],"SLM,":[63],"statistical":[65],"of":[67,138],"word":[69,143],"on":[70,115,149],"immediately":[71],"preceding":[72,74],"words,":[73],"heads,":[76],"non-terminal":[77],"labels,":[78],"etc.,":[79],"parameterized":[81],"overlapping":[83],"dependencies.":[85],"Statistical":[86],"parser":[90],"tagger":[92],"used":[93,106],"SLM":[96],"also":[97,147],"have":[98],"like":[100,111],"structure.":[101],"Deleted":[102],"interpolation":[103,132],"has":[104],"been":[105],"to":[107],"combine":[108],"these":[109],"models.":[112],"We":[113],"demonstrate":[114],"two":[116],"different":[117],"corpora":[118],"WSJ":[120],"Switchboard":[122,151],"that":[124],"more":[125],"recent":[126],"modified":[127],"strategies":[129],"nonlinear":[131],"considerably":[134],"lower":[135],"perplexity":[137],"Improvement":[141],"error":[144],"rate":[145],"demonstrated":[148],"corpus.":[152],"1.":[153]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}