{"id":"https://openalex.org/W3128216712","doi":"https://doi.org/10.1145/3443279.3443307","title":"A Comparative Study of Dictionary-based and Machine Learning-based Named Entity Recognition in Pashto","display_name":"A Comparative Study of Dictionary-based and Machine Learning-based Named Entity Recognition in Pashto","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3128216712","doi":"https://doi.org/10.1145/3443279.3443307","mag":"3128216712"},"language":"en","primary_location":{"id":"doi:10.1145/3443279.3443307","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","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/A5067234910","display_name":"Rafiullah Momand","orcid":null},"institutions":[{"id":"https://openalex.org/I19231517","display_name":"Kabul University","ror":"https://ror.org/02ht5pq60","country_code":"AF","type":"education","lineage":["https://openalex.org/I19231517"]}],"countries":["AF"],"is_corresponding":true,"raw_author_name":"Rafiullah Momand","raw_affiliation_strings":["Kabul University, Kabul, Afghanistan"],"affiliations":[{"raw_affiliation_string":"Kabul University, Kabul, Afghanistan","institution_ids":["https://openalex.org/I19231517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038624327","display_name":"Shakirullah Waseeb","orcid":"https://orcid.org/0000-0003-4790-5141"},"institutions":[{"id":"https://openalex.org/I3131932481","display_name":"Nangarhar University","ror":"https://ror.org/05n47cs30","country_code":"AF","type":"education","lineage":["https://openalex.org/I3131932481"]}],"countries":["AF"],"is_corresponding":false,"raw_author_name":"Shakirullah Waseeb","raw_affiliation_strings":["Nangarhar University, Nangarhar, Afghanistan"],"affiliations":[{"raw_affiliation_string":"Nangarhar University, Nangarhar, Afghanistan","institution_ids":["https://openalex.org/I3131932481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074823651","display_name":"Ahmad Masood Latif","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126853","display_name":"Polytechnical University of Kabul","ror":"https://ror.org/0451w9n55","country_code":"AF","type":"education","lineage":["https://openalex.org/I4210126853"]}],"countries":["AF"],"is_corresponding":false,"raw_author_name":"Ahmad Masood Latif Rai","raw_affiliation_strings":["Kabul Polytechnic University, Kabul, Afghanistan"],"affiliations":[{"raw_affiliation_string":"Kabul Polytechnic University, Kabul, Afghanistan","institution_ids":["https://openalex.org/I4210126853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067234910"],"corresponding_institution_ids":["https://openalex.org/I19231517"],"apc_list":null,"apc_paid":null,"fwci":0.6796,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.77921702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9977999925613403,"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":0.9972000122070312,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.8486554622650146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8369107246398926},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.8234937191009521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8044866323471069},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7688714861869812},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6393728256225586},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.615619421005249},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6039628386497498},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5853527784347534},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.5511049628257751},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.5231938362121582}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8486554622650146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8369107246398926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.8234937191009521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8044866323471069},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7688714861869812},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6393728256225586},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.615619421005249},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6039628386497498},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5853527784347534},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.5511049628257751},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.5231938362121582},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3443279.3443307","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W135458787","https://openalex.org/W336063547","https://openalex.org/W614190919","https://openalex.org/W1538261701","https://openalex.org/W1989420656","https://openalex.org/W2016698607","https://openalex.org/W2026691180","https://openalex.org/W2119695548","https://openalex.org/W2120811238","https://openalex.org/W2129311323","https://openalex.org/W2137715029","https://openalex.org/W2175108069","https://openalex.org/W2215206286","https://openalex.org/W2548286085","https://openalex.org/W3159921092","https://openalex.org/W4238254613","https://openalex.org/W6678460196","https://openalex.org/W6686138033","https://openalex.org/W7067687685"],"related_works":["https://openalex.org/W11196620","https://openalex.org/W2614126974","https://openalex.org/W1964783010","https://openalex.org/W2759598007","https://openalex.org/W4399144739","https://openalex.org/W2916255597","https://openalex.org/W3202659824","https://openalex.org/W3006227201","https://openalex.org/W2334378031","https://openalex.org/W2251120091"],"abstract_inverted_index":{"Information":[0],"Extraction":[1],"(IE)":[2],"is":[3,23],"the":[4,24,82,91,146],"process":[5],"of":[6,21,26,28,93,111,129,164],"extracting":[7],"structured":[8],"information":[9],"from":[10,157],"unstructured":[11],"text":[12],"using":[13],"natural":[14],"language":[15],"processing":[16],"(NLP).":[17],"One":[18],"important":[19,41],"sub-task":[20],"IE":[22],"extraction":[25],"names":[27,110,128],"persons,":[29,112,130],"places,":[30,113],"and":[31,53,87,114,132,168],"organizations,":[32,133],"called":[33],"Named":[34],"Entity":[35],"Recognition":[36],"(NER).":[37],"NER":[38,94,106,122],"plays":[39],"an":[40],"role":[42],"in":[43,72,90,116],"many":[44],"NLP":[45],"applications":[46],"such":[47],"as":[48],"Question":[49],"Answering,":[50],"Machine":[51],"Translation,":[52],"Text":[54],"Summarization.":[55],"It":[56],"has":[57,69],"been":[58],"widely":[59],"studied":[60],"for":[61,75,85,100,108,145,166,170],"high-resource":[62],"languages":[63,89],"like":[64],"English.":[65],"However,":[66],"no":[67],"research":[68,83],"taken":[70],"place":[71],"this":[73],"regard":[74],"Pashto.":[76,101],"We":[77,102,148],"hypothesized":[78],"that":[79,123,139,176],"based":[80,180],"on":[81,153],"done":[84],"English":[86],"other":[88],"area":[92],"a":[95,120,136,154],"system":[96],"can":[97],"be":[98],"developed":[99,104],"have":[103,149],"two":[105],"systems":[107,152],"detecting":[109],"organizations":[115],"Pashto":[117],"text.":[118],"First,":[119],"dictionary-based":[121,171],"uses":[124,140],"three":[125],"dictionaries":[126],"containing":[127],"locations,":[131],"respectively.":[134],"Second,":[135],"learning-based":[137],"approach":[138],"Hidden":[141],"Markov":[142],"Model":[143],"(HMM)":[144],"task.":[147],"evaluated":[150],"both":[151],"dataset":[155],"collected":[156],"sports":[158],"news.":[159],"Our":[160,173],"evaluation":[161],"showed":[162],"F-Measure":[163],"82%":[165],"HMM":[167,177],"60%":[169],"NER.":[172,181],"findings":[174],"highlight":[175],"outperforms":[178],"dictionary":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}