{"id":"https://openalex.org/W4416251303","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227844","title":"Optimized Domain-Specific Text Processing with Keyword Knowledge Distillation (KKD)","display_name":"Optimized Domain-Specific Text Processing with Keyword Knowledge Distillation (KKD)","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251303","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227844"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5009928964","display_name":"Momojit Biswas","orcid":"https://orcid.org/0000-0003-2820-0867"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Momojit Biswas","raw_affiliation_strings":["TCS Research,Kolkata,India"],"affiliations":[{"raw_affiliation_string":"TCS Research,Kolkata,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085329924","display_name":"Anmol Singhal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anmol Singhal","raw_affiliation_strings":["TCS Research,New Delhi,India"],"affiliations":[{"raw_affiliation_string":"TCS Research,New Delhi,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031939006","display_name":"Preethu Rose Anish","orcid":"https://orcid.org/0009-0001-7279-8993"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preethu Rose Anish","raw_affiliation_strings":["TCS Research,Pune,India"],"affiliations":[{"raw_affiliation_string":"TCS Research,Pune,India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009928964"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19461196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8521000146865845,"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":0.8521000146865845,"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":0.02280000038444996,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.012400000356137753,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/vocabulary","display_name":"Vocabulary","score":0.5277000069618225},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5221999883651733},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5105999708175659},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4916999936103821},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43309998512268066},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.36660000681877136},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3562000095844269},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.34279999136924744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7818999886512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6291999816894531},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6184999942779541},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4207000136375427},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3562000095844269},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1546425147","https://openalex.org/W2503275082","https://openalex.org/W2606964149","https://openalex.org/W2734608416","https://openalex.org/W2783538964","https://openalex.org/W2911489562","https://openalex.org/W2923014074","https://openalex.org/W2946794439","https://openalex.org/W2963748441","https://openalex.org/W2963809228","https://openalex.org/W2970120757","https://openalex.org/W3035030897","https://openalex.org/W3099950029","https://openalex.org/W3103585424","https://openalex.org/W3105966348","https://openalex.org/W3160137267","https://openalex.org/W3174544005","https://openalex.org/W3186492090","https://openalex.org/W3202026671","https://openalex.org/W4285261698","https://openalex.org/W4285287081","https://openalex.org/W4385570191","https://openalex.org/W4385573834","https://openalex.org/W4389520760"],"related_works":[],"abstract_inverted_index":{"The":[0,142],"generative":[1],"and":[2,36,46,64,117,138,151,200],"reasoning":[3],"capabilities":[4],"of":[5,42,123,175,198],"Pre-Trained":[6],"Language":[7,17],"Models":[8],"(PLMs)":[9],"have":[10],"led":[11],"to":[12,29,31,39,59,100,160],"significant":[13],"advancements":[14],"in":[15,53,114],"Natural":[16],"Understanding":[18],"(NLU).":[19],"However,":[20],"PLMs":[21,52],"face":[22],"two":[23],"main":[24],"challenges.":[25],"Firstly,":[26],"they":[27],"struggle":[28],"generalize":[30],"specialized":[32],"domains":[33,119],"like":[34],"Legal":[35,116],"Finance":[37,118],"due":[38,58],"the":[40,115,161,167,176,181],"prevalence":[41],"complex":[43],"domain-specific":[44,96,110,163],"vocabulary":[45],"intricate":[47],"sentence":[48],"structures.":[49],"Secondly,":[50],"deploying":[51],"real-world":[54],"applications":[55],"is":[56],"difficult":[57],"their":[60],"high":[61,157],"memory":[62],"requirements":[63],"computational":[65],"demands.":[66],"To":[67],"address":[68],"these":[69],"issues,":[70],"we":[71],"propose":[72],"Keyword":[73],"Knowledge":[74,88],"Distillation":[75,89],"(KKD),":[76],"a":[77,95,101,121,196],"novel":[78],"approach":[79],"for":[80],"in-domain":[81],"pre-training":[82],"using":[83,146],"selective":[84],"keyword":[85],"masking":[86],"during":[87],"(KD).":[90],"KKD":[91,113,147],"transfers":[92],"knowledge":[93],"from":[94],"Teacher":[97,164,177],"BERT":[98,105],"model":[99,106,169,183],"smaller,":[102],"efficient":[103],"Student":[104,143,168,182],"while":[107,154,180],"preserving":[108],"critical":[109],"information.We":[111],"evaluate":[112],"across":[120,195],"range":[122],"downstream":[124],"tasks,":[125],"including":[126],"multilabel":[127],"classification,":[128,130],"multiclass":[129],"extractive":[131],"question":[132,136],"answering,":[133,137],"regression,":[134],"multiple-choice":[135],"named":[139],"entity":[140],"recognition.":[141],"models":[144],"trained":[145,170,184],"are":[148],"40%":[149],"smaller":[150],"60%":[152],"faster,":[153],"still":[155],"maintaining":[156],"performance":[158],"compared":[159],"original,":[162],"models.":[165],"Specifically,":[166],"with":[171,185],"Legal-Bert":[172],"preserves":[173],"96.4%":[174],"model\u2019s":[178],"performance,":[179],"Fin-Bert":[186],"retains":[187],"99.1%.":[188],"These":[189],"results":[190],"underscore":[191],"KKD\u2019s":[192],"impressive":[193],"effectiveness":[194],"variety":[197],"tasks":[199],"domains.":[201]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}