{"id":"https://openalex.org/W2165980427","doi":"https://doi.org/10.1109/icassp.2003.1198762","title":"The robustness of an almost-parsing language model given errorful training data","display_name":"The robustness of an almost-parsing language model given errorful training data","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W2165980427","doi":"https://doi.org/10.1109/icassp.2003.1198762","mag":"2165980427"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198762","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5106407183","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0001-9914-5311"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113657967","display_name":"Mary P. Harper","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.P. Harper","raw_affiliation_strings":["Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Stolcke","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106407183"],"corresponding_institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.5414,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83416583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"240"},"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/T10201","display_name":"Speech Recognition and Synthesis","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/trigram","display_name":"Trigram","score":0.948656439781189},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.9136245846748352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.833541750907898},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7454229593276978},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7384594678878784},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6948460936546326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6496914625167847},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6213392019271851},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5969986319541931},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.4981656074523926},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42561107873916626},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41234320402145386},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3766513466835022}],"concepts":[{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.948656439781189},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9136245846748352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833541750907898},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7454229593276978},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7384594678878784},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6948460936546326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6496914625167847},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6213392019271851},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5969986319541931},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.4981656074523926},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42561107873916626},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41234320402145386},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3766513466835022},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198762","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522575729","https://openalex.org/W1535015163","https://openalex.org/W1542847127","https://openalex.org/W1577804718","https://openalex.org/W1631260214","https://openalex.org/W1632114991","https://openalex.org/W1643320849","https://openalex.org/W1649222155","https://openalex.org/W1809152426","https://openalex.org/W1953828586","https://openalex.org/W2092654472","https://openalex.org/W2100506586","https://openalex.org/W2123893795","https://openalex.org/W2143866356","https://openalex.org/W2155693943","https://openalex.org/W2158195707","https://openalex.org/W2343954916","https://openalex.org/W4388885063","https://openalex.org/W6632145054","https://openalex.org/W6634675184","https://openalex.org/W6636649193","https://openalex.org/W6636811518","https://openalex.org/W6638250965","https://openalex.org/W6674504384","https://openalex.org/W6858629103"],"related_works":["https://openalex.org/W2105076537","https://openalex.org/W2020757772","https://openalex.org/W2041167939","https://openalex.org/W2072223048","https://openalex.org/W2551914602","https://openalex.org/W2964047924","https://openalex.org/W1620568205","https://openalex.org/W2950575438","https://openalex.org/W2053242504","https://openalex.org/W79835312"],"abstract_inverted_index":{"An":[0],"almost-parsing":[1],"language":[2,46,66,87],"model":[3,47,88],"has":[4,48],"been":[5,49],"developed":[6],"(Wang":[7],"and":[8,23,55,64,92,115],"Harper":[9],"2002)":[10],"that":[11,36],"provides":[12],"a":[13,29,34],"framework":[14],"for":[15],"tightly":[16],"integrating":[17],"multiple":[18],"knowledge":[19],"sources.":[20],"Lexical":[21],"features":[22],"syntactic":[24],"constraints":[25],"are":[26],"integrated":[27],"into":[28],"uniform":[30],"linguistic":[31],"structure":[32],"(called":[33],"SuperARV)":[35],"is":[37],"associated":[38],"with":[39],"words":[40],"in":[41],"the":[42,69,83,86,112],"lexicon.":[43],"The":[44],"SuperARV":[45],"found":[50],"able":[51],"to":[52,61,89,101,104],"reduce":[53],"perplexity":[54],"word":[56],"error":[57],"rate":[58],"(WER)":[59],"compared":[60],"trigram,":[62],"part-of-speech-based,":[63],"parser-based":[65],"models":[67],"on":[68,111],"DARPA":[70,113],"Wall":[71],"Street":[72],"Journal":[73],"(WSJ)":[74],"CSR":[75,119],"task.":[76],"In":[77],"this":[78],"paper":[79],"we":[80],"further":[81],"investigate":[82],"robustness":[84],"of":[85],"possibly":[90],"inconsistent":[91],"flawed":[93],"training":[94],"data,":[95],"as":[96,98],"well":[97],"its":[99],"ability":[100],"scale":[102],"up":[103],"sophisticated":[105],"LVCSR":[106],"tasks":[107],"by":[108],"comparing":[109],"performance":[110],"WSJ":[114],"Hub4":[116],"(Broadcast":[117],"News)":[118],"tasks.":[120]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}