{"id":"https://openalex.org/W7203699267","doi":"https://doi.org/10.17632/d74sjfczch","title":"KazakhStopEval: Stop-Word Inventories, Validation Benchmarks, and NLP Evaluation Artifacts for Kazakh Library OCR Collections","display_name":"KazakhStopEval: Stop-Word Inventories, Validation Benchmarks, and NLP Evaluation Artifacts for Kazakh Library OCR Collections","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203699267","doi":"https://doi.org/10.17632/d74sjfczch"},"language":"en","primary_location":{"id":"doi:10.17632/d74sjfczch","doi":"https://doi.org/10.17632/d74sjfczch","is_oa":true,"landing_page_url":"https://doi.org/10.17632/d74sjfczch","pdf_url":null,"source":{"id":"https://openalex.org/S7407050775","display_name":"Mendeley Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17632/d74sjfczch","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073124571","display_name":"Iskander Akhmetov","orcid":"https://orcid.org/0000-0002-3221-9352","observed_orcids":["https://orcid.org/0000-0002-3221-9352"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Akhmetov, Iskander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5073124571"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6973000168800354,"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":0.6973000168800354,"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":0.08229999989271164,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.06689999997615814,"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/kazakh-language","display_name":"Kazakh language","score":0.8550000190734863},{"id":"https://openalex.org/keywords/genre-classification","display_name":"genre classification","score":0.6069999933242798},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7099999785423279},{"id":"https://openalex.org/keywords/agglutinative-morphology","display_name":"agglutinative morphology","score":0.9390000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921000123023987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6998999714851379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6703000068664551},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6424000263214111},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6075999736785889},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5724999904632568},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5347999930381775},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.3305000066757202},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2994543612","wikidata":"https://www.wikidata.org/wiki/Q22806","display_name":"National library","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.2556999921798706}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.17632/d74sjfczch","doi":"https://doi.org/10.17632/d74sjfczch","is_oa":true,"landing_page_url":"https://doi.org/10.17632/d74sjfczch","pdf_url":null,"source":{"id":"https://openalex.org/S7407050775","display_name":"Mendeley Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"},{"id":"doi:10.17632/d74sjfczch.1","doi":"https://doi.org/10.17632/d74sjfczch.1","is_oa":true,"landing_page_url":"https://doi.org/10.17632/d74sjfczch.1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050775","display_name":"Mendeley Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"}],"best_oa_location":{"id":"doi:10.17632/d74sjfczch","doi":"https://doi.org/10.17632/d74sjfczch","is_oa":true,"landing_page_url":"https://doi.org/10.17632/d74sjfczch","pdf_url":null,"source":{"id":"https://openalex.org/S7407050775","display_name":"Mendeley Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4362636547","https://openalex.org/W7171039223","https://openalex.org/W7223225673","https://openalex.org/W6893091309","https://openalex.org/W7172379850","https://openalex.org/W7171743650","https://openalex.org/W6891957153","https://openalex.org/W7164052188","https://openalex.org/W7223110064","https://openalex.org/W4297847047"],"abstract_inverted_index":{"###":[0,66,179],"Dataset":[1],"Description":[2],"This":[3],"dataset":[4],"provides":[5],"the":[6,20,53,57,69],"stop-word":[7],"inventories,":[8],"manual":[9,120],"validation":[10],"sets,":[11],"baseline":[12],"stemmer,":[13],"and":[14,32,61,123,162],"downstream":[15],"evaluation":[16],"benchmarks":[17],"described":[18],"in":[19],"paper":[21],"*\"Building":[22],"an":[23],"NLP":[24],"Pipeline":[25],"for":[26,132,177,181],"Kazakh-Language":[27],"Library":[28,55],"Collections:":[29],"Stop-Word":[30],"Extraction":[31],"Genre":[33],"Classification\"*":[34],"(AIST":[35],"2026":[36],"/":[37,190,193],"CCIS).":[38],"The":[39],"resources":[40],"are":[41],"derived":[42],"from":[43,52],"a":[44],"122.56-million-token":[45],"Kazakh-centred":[46],"corpus":[47],"combining":[48],"2,028":[49],"OCR-scanned":[50],"books":[51],"National":[54],"of":[56,59,68],"Republic":[58],"Kazakhstan":[60],"231,729":[62],"Kazakh":[63],"Wikipedia":[64],"articles.":[65],"Contents":[67],"Deposit:":[70],"1.":[71],"**Stop-Word":[72],"Inventories":[73],"(`stopwords/`):**":[74],"-":[75,81,90,95,101,114,127,138,153,171,183,196,211],"`grammar_dict.json`":[76],"(335":[77],"normalised":[78],"grammar-dictionary":[79],"terms)":[80],"`stopwords_single_tfidf.txt`":[82],"(2,991":[83],"statistical":[84],"single-token":[85],"candidates":[86],"at":[87],"5%":[88],"threshold)":[89],"`stopwords_collocation_phrases.txt`":[91],"(3,462":[92],"collocation":[93],"pairs)":[94],"`stopwords_combined.txt`":[96],"(3,414":[97],"combined":[98],"surface":[99],"forms)":[100],"`stopwords_multilingual.txt`":[102],"(3,930":[103],"multilingual":[104],"forms":[105],"including":[106],"Kazakh,":[107],"Russian,":[108],"English)":[109],"2.":[110],"**Validation":[111],"Data":[112],"(`validation/`):**":[113],"`manual_stopword_review_sample_200_labeled.csv`":[115],"(stratified":[116],"200-word":[117],"sample":[118],"with":[119,149],"expert":[121],"annotations":[122],"Wilson":[124],"confidence":[125],"intervals)":[126],"`manual_stopword_review_template.csv`":[128],"(unlabeled":[129],"annotation":[130],"template":[131],"replication)":[133],"3.":[134],"**Evaluation":[135],"Sets":[136],"(`proxy_evaluation/`):**":[137],"`queries.csv`":[139],"&":[140,155,168],"`qrels.csv`":[141],"(50":[142],"queries:":[143],"39":[144],"topical":[145],"+":[146],"11":[147],"known-item,":[148],"associated":[150],"relevance":[151],"judgments)":[152],"`classification_metrics.csv`":[154],"`topic_metrics.csv`":[156],"(ablation":[157],"results":[158],"across":[159],"configurations":[160],"A\u2013E":[161],"stemmed":[163],"variant":[164],"F)":[165],"4.":[166],"**Tools":[167],"Baselines":[169],"(`tools/`):**":[170],"`kazakh_stemmer.py`":[172],"(lightweight":[173],"rule-based":[174],"suffix-stripping":[175],"stemmer":[176],"Kazakh)":[178],"Metadata":[180],"Mendeley:":[182],"**Category:**":[184],"Computer":[185],"Science":[186],">":[187],"Artificial":[188],"Intelligence":[189],"Computational":[191],"Linguistics":[192],"Information":[194],"Retrieval":[195],"**Keywords:**":[197],"`Kazakh":[198],"NLP`,":[199],"`Stop":[200],"Words`,":[201],"`Digital":[202],"Libraries`,":[203],"`Low-Resource":[204],"Languages`,":[205],"`Information":[206],"Retrieval`,":[207],"`Agglutinative":[208],"Morphology`,":[209],"`LibRAG`":[210],"**License:**":[212],"CC":[213],"BY":[214],"4.0":[215]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-19T00:00:00"}