{"id":"https://openalex.org/W80634668","doi":"https://doi.org/10.21437/icslp.1998-664","title":"A bootstrap technique for building domain-dependent language models","display_name":"A bootstrap technique for building domain-dependent language models","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W80634668","doi":"https://doi.org/10.21437/icslp.1998-664","mag":"80634668"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-664","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5111944718","display_name":"Ganesh N. Ramaswamy","orcid":"https://orcid.org/0009-0002-8015-0844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ganesh N. Ramaswamy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063122680","display_name":"Harry Printz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harry Printz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112379859","display_name":"P.S. Gopalakrishnan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ponani S. Gopalakrishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0999,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80370077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 0611","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.992900013923645,"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":0.9797999858856201,"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":0.8582168817520142},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7911940813064575},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7385357618331909},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6529901027679443},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.568413496017456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5544711351394653},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.547325849533081},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5450499653816223},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48630866408348083},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4751427173614502},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4530099332332611},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4305574297904968},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4170586168766022},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.41599223017692566},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.342262327671051},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.30032801628112793},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09734505414962769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582168817520142},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7911940813064575},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7385357618331909},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6529901027679443},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.568413496017456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5544711351394653},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.547325849533081},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5450499653816223},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48630866408348083},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4751427173614502},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4530099332332611},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4305574297904968},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4170586168766022},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41599223017692566},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.342262327671051},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30032801628112793},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09734505414962769},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1998-664","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1538424569","https://openalex.org/W1597533204","https://openalex.org/W1718044877","https://openalex.org/W2121227244","https://openalex.org/W2147451362","https://openalex.org/W2155388323","https://openalex.org/W2164517999","https://openalex.org/W2441154163"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"In":[0],"this":[1,129],"paper,":[2],"we":[3,102,110],"propose":[4],"a":[5,17,22,39,54,80,104,171],"new":[6,30,108],"bootstrap":[7,150],"technique":[8],"to":[9,28,37,68,88,98,120,132,146,193],"build":[10,38],"domain-dependent":[11],"language":[12,41,77,115],"models.":[13],"We":[14,43,73,117,141],"assume":[15,45],"that":[16,95,191],"seed":[18,202],"corpus":[19,94,199,203],"consisting":[20,52],"of":[21,25,48,53,57,71,107,164,173,181,185],"small":[23],"amount":[24,56],"data":[26,58],"relevant":[27,67,97],"the":[29,46,69,75,85,92,99,113,125,149,165,176,182,186,189,197,201,215],"domain":[31,70],"is":[32,35,139,212],"available,":[33],"which":[34,62],"used":[36],"reference":[40,76,114],"model.":[42,116],"also":[44,142],"availability":[47],"an":[49],"external":[50,93,126,198],"corpus,":[51,127],"large":[55],"from":[59,91,124],"various":[60],"sources,":[61],"need":[63,192],"not":[64],"be":[65,194],"directly":[66],"interest.":[72],"use":[74],"model":[78],"and":[79,128,159,175,188,200],"suitable":[81],"metric,":[82],"such":[83,152],"as":[84,153],"perplexity":[86],"measure,":[87],"select":[89,121],"sentences":[90,123],"are":[96,178,204],"domain.":[100],"Once":[101],"have":[103],"sufficient":[105],"number":[106],"sentences,":[109],"can":[111],"rebuild":[112],"then":[118],"continue":[119],"additional":[122],"process":[130],"continues":[131],"iterate":[133],"until":[134],"some":[135],"satisfactory":[136],"termination":[137],"point":[138],"achieved.":[140],"describe":[143],"several":[144],"methods":[145],"further":[147],"enhance":[148],"technique,":[151],"combining":[154],"it":[155],"with":[156],"mixture":[157],"modeling":[158],"class-based":[160],"modeling.":[161],"The":[162],"performance":[163],"proposed":[166],"approach":[167,187],"was":[168],"evaluated":[169],"through":[170],"set":[172],"experiments,":[174],"results":[177],"discussed.":[179],"Analysis":[180],"convergence":[183],"properties":[184],"conditions":[190],"satisfied":[195],"by":[196],"highlighted,":[205],"but":[206],"detailed":[207],"work":[208],"on":[209],"these":[210],"issues":[211],"deferred":[213],"for":[214],"future.":[216]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}