{"id":"https://openalex.org/W3136630482","doi":"https://doi.org/10.1109/bigdata50022.2020.9377810","title":"Fine-Tuning Language Models For Semi-Supervised Text Mining","display_name":"Fine-Tuning Language Models For Semi-Supervised Text Mining","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3136630482","doi":"https://doi.org/10.1109/bigdata50022.2020.9377810","mag":"3136630482"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","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/A5100443903","display_name":"Xinyu Chen","orcid":"https://orcid.org/0000-0003-1951-5015"},"institutions":[{"id":"https://openalex.org/I4210138417","display_name":"Verint Systems (United States)","ror":"https://ror.org/03fqhrc68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138417"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyu Chen","raw_affiliation_strings":["Verint - Next IT, Spokane, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Verint - Next IT, Spokane, WA, USA","institution_ids":["https://openalex.org/I4210138417"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046481287","display_name":"Ian Beaver","orcid":"https://orcid.org/0000-0003-0865-1214"},"institutions":[{"id":"https://openalex.org/I4210138417","display_name":"Verint Systems (United States)","ror":"https://ror.org/03fqhrc68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138417"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Beaver","raw_affiliation_strings":["Verint - Next IT, Spokane, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Verint - Next IT, Spokane, WA, USA","institution_ids":["https://openalex.org/I4210138417"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086018905","display_name":"Cynthia Freeman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138417","display_name":"Verint Systems (United States)","ror":"https://ror.org/03fqhrc68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138417"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cynthia Freeman","raw_affiliation_strings":["Verint - Next IT, Spokane, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Verint - Next IT, Spokane, WA, USA","institution_ids":["https://openalex.org/I4210138417"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210138417"],"apc_list":null,"apc_paid":null,"fwci":0.2709,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67060789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3608","last_page":"3617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9939000010490417,"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":0.827095091342926},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7396026253700256},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6859071254730225},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6571812033653259},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6485565900802612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6405959129333496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5645231008529663},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4715675711631775},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.44456902146339417},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.41417741775512695},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4112367033958435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827095091342926},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7396026253700256},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6859071254730225},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6571812033653259},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6485565900802612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6405959129333496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5645231008529663},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4715675711631775},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.44456902146339417},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.41417741775512695},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4112367033958435},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W1493526108","https://openalex.org/W1532325895","https://openalex.org/W1840435438","https://openalex.org/W2001032894","https://openalex.org/W2102524069","https://openalex.org/W2129250947","https://openalex.org/W2131681506","https://openalex.org/W2132914434","https://openalex.org/W2139956879","https://openalex.org/W2150102617","https://openalex.org/W2174706414","https://openalex.org/W2334889010","https://openalex.org/W2605181250","https://openalex.org/W2739351760","https://openalex.org/W2741943936","https://openalex.org/W2752172973","https://openalex.org/W2790235966","https://openalex.org/W2803475843","https://openalex.org/W2896457183","https://openalex.org/W2897197428","https://openalex.org/W2897438987","https://openalex.org/W2898541610","https://openalex.org/W2908510526","https://openalex.org/W2921848006","https://openalex.org/W2923996791","https://openalex.org/W2927746189","https://openalex.org/W2951514583","https://openalex.org/W2962739339","https://openalex.org/W2963325132","https://openalex.org/W2963341956","https://openalex.org/W2963639288","https://openalex.org/W2963846996","https://openalex.org/W2964074409","https://openalex.org/W2964165804","https://openalex.org/W2965373594","https://openalex.org/W2969545804","https://openalex.org/W2970352191","https://openalex.org/W2970641574","https://openalex.org/W2986063762","https://openalex.org/W2988217457","https://openalex.org/W2998702515","https://openalex.org/W3001309956","https://openalex.org/W3019927586","https://openalex.org/W3034238904","https://openalex.org/W3037585619","https://openalex.org/W3086105743","https://openalex.org/W3099768174","https://openalex.org/W3104033643","https://openalex.org/W4213009331","https://openalex.org/W4294554825","https://openalex.org/W6675528751","https://openalex.org/W6681025260","https://openalex.org/W6681875376","https://openalex.org/W6685380521","https://openalex.org/W6703074907","https://openalex.org/W6737236263","https://openalex.org/W6743384090","https://openalex.org/W6745097924","https://openalex.org/W6748452836","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W1583765404","https://openalex.org/W4214653257","https://openalex.org/W2055438207","https://openalex.org/W2521424917","https://openalex.org/W3040203686","https://openalex.org/W4249524554","https://openalex.org/W2349021146","https://openalex.org/W35583307","https://openalex.org/W4398294854","https://openalex.org/W2436192316"],"abstract_inverted_index":{"The":[0],"dimensionality":[1],"of":[2,63,78,101,114,140,160,178,205,238,264],"traditional":[3],"text":[4,11,17,68,103,122,134,300],"representation":[5],"is":[6,13,30,43,243],"large,":[7],"but":[8],"the":[9,90,99,112,138,158,179,183,206,211,218,239,247,253,265,273],"underlying":[10],"data":[12,208],"sparse.":[14],"This":[15,86],"makes":[16],"clustering":[18,69,104,109,135,220,250,278,287,301],"a":[19,50,64,75,171,244],"very":[20],"challenging":[21],"task.":[22],"Using":[23],"language":[24,47,84,91,117,162,197,230,259,297],"models":[25,48,92,118,163,198,231,298],"and":[26,137,252,257,280,302],"deep":[27],"contextualized":[28,96],"representations":[29,169],"promising":[31],"in":[32,153,189],"many":[33],"Natural":[34],"Language":[35],"Processing":[36],"(NLP)":[37],"tasks.":[38,57,70,105,288],"However,":[39],"some":[40],"task-specific":[41,95,168],"guidance":[42,293],"necessary":[44],"to":[45,49,54,81,93,125,127,165,186,203,209,224,294],"adapt":[46],"novel":[51,154,286],"domain":[52],"or":[53,156,227,271],"particular":[55],"downstream":[56,102,219,249],"We":[58,106],"present":[59],"an":[60],"empirical":[61],"study":[62],"pipeline":[65,131],"for":[66,144,150,255,276,284,299],"semi-supervised":[67],"Our":[71,146],"proposed":[72],"method":[73],"utilizes":[74],"small":[76,175],"number":[77],"labeled":[79,141,172,200],"samples":[80,142],"fine-tune":[82],"pre-trained":[83],"models.":[85,260],"fine-tuning":[87,258],"step":[88],"adapts":[89],"produce":[94,166],"representations,":[97],"improving":[98],"performance":[100],"evaluate":[107],"two":[108,285],"algorithms":[110],"using":[111,170],"output":[113],"three":[115],"different":[116],"on":[119],"six":[120],"real-world":[121],"mining":[123,152],"tasks":[124,279],"demonstrate":[126],"what":[128],"extent":[129],"this":[130],"can":[132],"improve":[133],"accuracy":[136,221],"amount":[139],"needed":[143],"improvement.":[145],"experiments":[147,216],"show":[148,217],"that":[149,191],"topic":[151],"domains":[155,190],"surfacing":[157],"intentions":[159],"abstracts,":[161],"begin":[164],"better":[167],"subset":[173],"as":[174,176],"0.5%":[177],"task":[180,207,240,266],"data.":[181,241],"On":[182],"other":[184],"hand,":[185],"find":[187],"topics":[188],"are":[192,232],"overlapping":[193],"with":[194,234,262],"pre-training":[195],"corpora,":[196],"need":[199],"subsets":[201],"closer":[202],"1.0%":[204],"overcome":[210],"catastrophic":[212],"forgetting":[213],"problem.":[214],"Further":[215],"gain":[222],"begins":[223],"slow":[225],"down":[226],"plateau":[228],"if":[229],"fine-tuned":[233],"more":[235],"than":[236],"5%":[237],"There":[242],"trade-off":[245],"between":[246],"desired":[248],"quality":[251],"cost":[254],"labeling":[256],"Fine-tuned":[261],"2.5%":[263],"data,":[267],"our":[268],"approach":[269],"matches":[270],"exceeds":[272],"current":[274],"state-of-the-art":[275],"several":[277],"provides":[281],"baseline":[282],"results":[283,290],"These":[289],"provide":[291],"solid":[292],"utilize":[295],"powerful":[296],"information":[303],"retrieval":[304],"practitioners.":[305]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}