{"id":"https://openalex.org/W6930935477","doi":"https://doi.org/10.5281/zenodo.15917448","title":"EDUCATIONAL AND LINGUISTIC ASPECTS OF TEXT PREPROCESSING IN PASHTO","display_name":"EDUCATIONAL AND LINGUISTIC ASPECTS OF TEXT PREPROCESSING IN PASHTO","publication_year":2025,"publication_date":"2025-06-29","ids":{"openalex":"https://openalex.org/W6930935477","doi":"https://doi.org/10.5281/zenodo.15917448"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15917448","doi":"https://doi.org/10.5281/zenodo.15917448","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15917448","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.15917448","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Abdul Qadir","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20561161","display_name":"University of Balochistan","ror":"https://ror.org/04bf33n91","country_code":"PK","type":"education","lineage":["https://openalex.org/I20561161"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Abdul Qadir","raw_affiliation_strings":["Department of Computer Science, University of Balochistan Quetta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Balochistan Quetta","institution_ids":["https://openalex.org/I20561161"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ihsan Ullah","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20561161","display_name":"University of Balochistan","ror":"https://ror.org/04bf33n91","country_code":"PK","type":"education","lineage":["https://openalex.org/I20561161"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ihsan Ullah","raw_affiliation_strings":["Department of Computer Science, University of Balochistan Quetta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Balochistan Quetta","institution_ids":["https://openalex.org/I20561161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20561161"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30698028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.00039999998989515007,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pashto","display_name":"Pashto language","score":0.9929999709129333},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.9810000061988831},{"id":"https://openalex.org/keywords/orthographic-normalization","display_name":"orthographic normalization","score":0.9160000085830688},{"id":"https://openalex.org/keywords/stemming","display_name":"stemming","score":0.8849999904632568},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.9179999828338623},{"id":"https://openalex.org/keywords/corpus-development","display_name":"corpus development","score":0.6700000166893005},{"id":"https://openalex.org/keywords/educational-texts","display_name":"educational texts","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649999856948853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6980000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6335999965667725},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5113999843597412},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C2778689934","wikidata":"https://www.wikidata.org/wiki/Q1313396","display_name":"Headline","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.15917448","doi":"https://doi.org/10.5281/zenodo.15917448","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15917448","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.15917449","doi":"https://doi.org/10.5281/zenodo.15917449","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15917449","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.5281/zenodo.15917448","doi":"https://doi.org/10.5281/zenodo.15917448","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15917448","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"sustainable_development_goals":[{"score":0.4156000018119812,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"sustainable_development_goals_aurora":[{"score":0.6411718726158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract:This":[0],"paper":[1],"introduces":[2],"foundational":[3],"text":[4,124],"preprocessing":[5,121],"strategies":[6],"designed":[7],"for":[8,88,104],"the":[9,33,117],"Pashto":[10,52,66,106],"language,":[11],"focusing":[12],"on":[13,65,75],"linguistic":[14,83],"structure,":[15],"educational":[16,67],"adaptation,":[17],"and":[18,27,47,60,68,91,97,111,127],"syntactic":[19],"modeling.":[20],"Given":[21],"Pashto's":[22],"complex":[23],"morphology,":[24],"diverse":[25],"dialects,":[26],"lack":[28],"of":[29,119],"standardized":[30],"digital":[31,112],"tools,":[32],"study":[34],"outlines":[35],"a":[36],"step-by-step":[37],"pipeline":[38],"including":[39],"orthographic":[40],"normalization,":[41],"rule-based":[42],"tokenization,":[43],"customized":[44],"stop-words":[45],"filtering,":[46],"light":[48],"stemming":[49],"suited":[50],"to":[51],"syntax.":[53],"The":[54,94],"work":[55],"further":[56],"explores":[57],"grammatical":[58],"tagging":[59],"lexical":[61],"refinement":[62],"with":[63],"emphasis":[64],"literary":[69],"terms.":[70],"Rather":[71],"than":[72],"relying":[73],"solely":[74],"machine":[76],"learning":[77],"models,":[78],"this":[79],"research":[80],"emphasizes":[81],"human-curated":[82],"rules,":[84],"making":[85],"it":[86],"suitable":[87],"academic,":[89],"pedagogical,":[90],"resource-building":[92],"contexts.":[93],"developed":[95],"scripts":[96],"processed":[98],"datasets":[99],"serve":[100],"as":[101],"baseline":[102],"tools":[103],"future":[105],"NLP":[107],"applications,":[108],"corpus":[109],"development,":[110],"resource":[113],"integration.":[114],"Results":[115],"highlight":[116],"importance":[118],"tailored":[120],"in":[122],"improving":[123],"quality,":[125],"readability,":[126],"annotation":[128],"consistency":[129],"across":[130],"domains.":[131]},"counts_by_year":[],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2025-10-10T00:00:00"}