{"id":"https://openalex.org/W4391528349","doi":"https://doi.org/10.1109/access.2024.3362645","title":"ACRF: Aggregated Conditional Random Field for Out of Vocab (OOV) Token Representation for Hindi NER","display_name":"ACRF: Aggregated Conditional Random Field for Out of Vocab (OOV) Token Representation for Hindi NER","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391528349","doi":"https://doi.org/10.1109/access.2024.3362645"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3362645","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3362645","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10422739.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10422739.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002585659","display_name":"Sumit Singh","orcid":"https://orcid.org/0000-0002-3292-4131"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumit Singh","raw_affiliation_strings":["Indian Institute of Information Technology Allahabad, Allahabad, India"],"raw_orcid":"https://orcid.org/0000-0002-3292-4131","affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Allahabad, Allahabad, India","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060052491","display_name":"Uma Shanker Tiwary","orcid":"https://orcid.org/0000-0001-7206-9013"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Uma Shanker Tiwary","raw_affiliation_strings":["Indian Institute of Information Technology Allahabad, Allahabad, India"],"raw_orcid":"https://orcid.org/0000-0001-7206-9013","affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Allahabad, Allahabad, India","institution_ids":["https://openalex.org/I26072440"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I26072440"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1943,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8095671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"22707","last_page":"22717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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/conditional-random-field","display_name":"Conditional random field","score":0.787452220916748},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.7087339162826538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6628382205963135},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6557767987251282},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4940543472766876},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4694490134716034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42320311069488525},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.383756548166275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24400711059570312},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0854586660861969},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.05158895254135132}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.787452220916748},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.7087339162826538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628382205963135},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6557767987251282},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4940543472766876},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4694490134716034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42320311069488525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.383756548166275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24400711059570312},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0854586660861969},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.05158895254135132},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3362645","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3362645","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10422739.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6efdec15324f4c7ba423951d94cfa011","is_oa":true,"landing_page_url":"https://doaj.org/article/6efdec15324f4c7ba423951d94cfa011","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 22707-22717 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3362645","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3362645","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10422739.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391528349.pdf","grobid_xml":"https://content.openalex.org/works/W4391528349.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1940872118","https://openalex.org/W2064675550","https://openalex.org/W2132187905","https://openalex.org/W2143345705","https://openalex.org/W2157331557","https://openalex.org/W2908510526","https://openalex.org/W2952230511","https://openalex.org/W2989969443","https://openalex.org/W3011594683","https://openalex.org/W3035390927","https://openalex.org/W3104415840","https://openalex.org/W3136221257","https://openalex.org/W3141108820","https://openalex.org/W3162486530","https://openalex.org/W3171396241","https://openalex.org/W4205883286","https://openalex.org/W4221167171","https://openalex.org/W4225513420","https://openalex.org/W4287854446","https://openalex.org/W4287889470","https://openalex.org/W4293649366","https://openalex.org/W4379875123","https://openalex.org/W4385245566","https://openalex.org/W4385477831","https://openalex.org/W4385572425","https://openalex.org/W4385572571","https://openalex.org/W4389519058","https://openalex.org/W4389523957","https://openalex.org/W6640267182","https://openalex.org/W6640362995","https://openalex.org/W6682238262","https://openalex.org/W6683738474","https://openalex.org/W6697154816","https://openalex.org/W6757817989","https://openalex.org/W6773695642","https://openalex.org/W6785668629","https://openalex.org/W6791709101","https://openalex.org/W6810092961"],"related_works":["https://openalex.org/W2384553807","https://openalex.org/W1557888283","https://openalex.org/W3089999372","https://openalex.org/W2265245145","https://openalex.org/W3110423299","https://openalex.org/W4312229285","https://openalex.org/W2510663906","https://openalex.org/W2078793151","https://openalex.org/W2886890203","https://openalex.org/W3080906831"],"abstract_inverted_index":{"Named":[0],"entities":[1,6],"are":[2,148],"random,":[3],"like":[4],"emerging":[5],"and":[7,131,184,196,232,234],"complex":[8,46],"entities.":[9],"Most":[10],"of":[11,62,76,98,111,174,177],"the":[12,41,59,63,96,138,155,175,197,205],"large":[13],"language":[14],"model\u2019s":[15],"tokenizers":[16],"have":[17,83],"fixed":[18],"vocab;":[19],"hence,":[20],"they":[21],"tokenize":[22],"out-of-vocab":[23],"(OOV)":[24,214],"words":[25,206],"into":[26],"multiple":[27],"sub-words":[28,38,213],"during":[29],"tokenisation.":[30],"During":[31],"fine-tuning":[32],"for":[33,48,57,102,189,204],"any":[34],"downstream":[35],"task,":[36],"these":[37,237],"(tokens)":[39],"make":[40],"named":[42,103],"entity":[43,53,104,187],"classification":[44,169],"more":[45,210],"since,":[47],"each":[49,77,190],"sub-word,":[50],"an":[51],"extra":[52],"type":[54],"is":[55,93,107,140],"assigned":[56],"utilizing":[58],"word":[60,191],"embedding":[61],"sub-word.":[64],"This":[65,134],"work":[66,135,222],"attempts":[67],"to":[68,119,186,216],"reduce":[69],"this":[70,80,221],"complexity":[71],"by":[72,115,165],"aggregating":[73],"token":[74,100,146],"embeddings":[75,101,110,147],"word.":[78,121],"In":[79,219],"work,":[81],"we":[82],"applied":[84,94],"Aggregated-CRF":[85],"(ACRF),":[86],"where":[87],"a":[88,116,120,167,224],"conditional":[89],"random":[90],"field":[91],"(CRF)":[92],"at":[95,109,159],"top":[97],"aggregated":[99],"prediction.":[105],"Aggregation":[106],"done":[108,125,164],"all":[112],"tokens":[113],"generated":[114],"tokenizer":[117],"corresponding":[118],"The":[122],"experiment":[123],"was":[124,163],"with":[126],"two":[127,228],"Hindi":[128,132],"datasets":[129],"(HiNER":[130],"Multiconer2).":[133],"showed":[136],"that":[137,200],"ACRF":[139,201],"better":[141,203],"than":[142,211],"vanilla":[143,217],"CRF":[144],"(where":[145],"not":[149],"aggregated).":[150],"Also,":[151],"our":[152],"result":[153,158],"outperformed":[154],"existing":[156],"best":[157],"HiNER":[160],"data,":[161,195],"which":[162,207],"applying":[166],"cross-entropy":[168],"layer.":[170],"Further,":[171],"An":[172],"analysis":[173,226],"impact":[176],"tokenization":[178],"has":[179],"been":[180],"conducted,":[181],"both":[182],"generally":[183],"according":[185],"types":[188],"present":[192],"in":[193,209],"test":[194],"results":[198],"show":[199],"performed":[202],"tokenized":[208],"one":[212],"compared":[215],"CRF.":[218],"addition,":[220],"conducts":[223],"comparative":[225],"between":[227],"transformer-based":[229],"models,":[230],"MuRIL-large":[231],"XLM-roberta-large":[233],"investigates":[235],"how":[236],"models":[238],"adopt":[239],"aggregation":[240],"strategy":[241],"based":[242],"on":[243],"OOV.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}