{"id":"https://openalex.org/W6944904156","doi":"https://doi.org/10.21227/anmp-va09","title":"Readability-Aware Summarization Dataset for Turkish","display_name":"Readability-Aware Summarization Dataset for Turkish","publication_year":2025,"publication_date":"2025-03-19","ids":{"openalex":"https://openalex.org/W6944904156","doi":"https://doi.org/10.21227/anmp-va09"},"language":"en","primary_location":{"id":"doi:10.21227/anmp-va09","is_oa":true,"landing_page_url":"https://doi.org/10.21227/anmp-va09","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/anmp-va09","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Duran, Mehmet Samet","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Duran, Mehmet Samet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Aytekin, Tevfik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aytekin, Tevfik","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.9071000218391418},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8514999747276306},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.6389999985694885},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6111999750137329},{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.5892000198364258},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5782999992370605},{"id":"https://openalex.org/keywords/text-simplification","display_name":"Text simplification","score":0.35679998993873596},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.33070001006126404}],"concepts":[{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.9071000218391418},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8514999747276306},{"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/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6583999991416931},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.6389999985694885},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5738999843597412},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48159998655319214},{"id":"https://openalex.org/C59415355","wikidata":"https://www.wikidata.org/wiki/Q3484781","display_name":"Text simplification","level":3,"score":0.35679998993873596},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C120012220","wikidata":"https://www.wikidata.org/wiki/Q1754533","display_name":"Source text","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/anmp-va09","is_oa":true,"landing_page_url":"https://doi.org/10.21227/anmp-va09","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.21227/anmp-va09","is_oa":true,"landing_page_url":"https://doi.org/10.21227/anmp-va09","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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","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":[{"score":0.6341116428375244,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,124],"dataset":[1,194,203,251],"is":[2,204,226,252],"constructed":[3],"in":[4,280],"a":[5,132,261,281],"study":[6],"that":[7,166,232],"addresses":[8],"the":[9,35,47,58,63,87,101,109,118,127,146,159,167,171,179,193,236,241,245,250,274],"gap":[10],"between":[11],"text":[12,95,122,231],"summarization":[13],"and":[14,26,83,120,142,197,221,276,289],"content":[15,130],"readability":[16,32,44,49,59,173],"for":[17,30,53,188,266,286],"diverse":[18,196],"Turkish-speaking":[19],"audiences.":[20],"It":[21,56],"contains":[22],"paired":[23],"original":[24,160],"texts":[25],"corresponding":[27],"summaries":[28],"optimized":[29],"different":[31],"levels":[33],"using":[34,162],"YOD":[36,48,137,268],"(Yeni":[37],"Okunabilirlik":[38],"D\u00fczeyi)":[39],"formula.YOD":[40],"Readibility":[41],"Metric:":[42],"Bezirci-Y\u0131lmaz":[43],"formula":[45],"defines":[46],"metric":[50,76],"specifically":[51],"designed":[52],"Turkish":[54],"texts.":[55],"calculates":[57],"score":[60],"based":[61],"on":[62],"average":[64,88],"number":[65],"of":[66,94,129,136,283],"polysyllabic":[67,81],"words":[68,82],"(three":[69],"or":[70],"more":[71,133],"syllables)":[72],"per":[73],"sentence.":[74],"The":[75,202],"assigns":[77],"weights":[78],"to":[79,107,158,164,178,240,255,272],"these":[80],"combines":[84],"them":[85],"with":[86,131,195],"sentence":[89,119],"length,":[90],"providing":[91],"an":[92],"assessment":[93],"complexity.Dataset":[96],"Creation":[97],"Logic:":[98],"To":[99,150,259],"create":[100],"dataset,":[102],"VBART-Large-Paraphrasing":[103],"model":[104],"was":[105,156,185],"employed":[106],"enhance":[108],"existing":[110],"datasets":[111],"by":[112],"generating":[113],"paraphrased":[114],"variations":[115],"at":[116],"both":[117,140,273,287],"full-":[121],"levels.":[123],"approach":[125],"permitted":[126],"derivation":[128],"extensive":[134],"range":[135],"values,":[138,144],"encompassing":[139],"higher":[141],"lower":[143],"from":[145,206,229],"same":[147],"source":[148],"material.":[149],"maintain":[151],"semantic":[152],"integrity,":[153],"each":[154,267],"paraphrase":[155],"compared":[157],"summary":[161],"BERTScore":[163],"verify":[165],"synthetic":[168,189,246],"data":[169,190,247],"achieved":[170],"intended":[172],"adjustments":[174],"while":[175],"remaining":[176],"faithful":[177],"source.":[180],"In":[181],"addition,":[182],"ChatGPT\u2019s":[183],"API":[184],"also":[186],"used":[187],"generation,":[191],"enriching":[192],"high-quality":[198],"rewritten":[199],"summaries. Dataset":[200],"Creation:":[201],"compiled":[205],"multiple":[207],"sources:":[208],"XLSUM":[209],"(970":[210],"entries),":[211,214,217,220],"TRNews":[212],"(5,000":[213],"MLSUM":[215],"(1,033":[216],"LR-SUM":[218],"(1,107":[219],"Wikipedia-trsummarization":[222],"(3,024":[223],"entries).":[224],"Sampling":[225],"done":[227],"hierarchically":[228],"longest":[230],"can":[233],"fit":[234],"into":[235],"tokenizer(vngrs-ai/VBART-Large-Paraphrasing)":[237],"without":[238],"truncation":[239],"shortest":[242],"content.":[243],"After":[244],"generation":[248],"process,":[249],"significantly":[253],"expanded":[254],"include":[256],"76,759":[257],"summaries.":[258],"guarantee":[260],"thorough":[262],"evaluation,":[263],"200":[264],"samples":[265],"level":[269],"are":[270],"allocated":[271],"test":[275,288],"validation":[277],"sets,":[278],"resulting":[279],"total":[282],"3200":[284],"examples":[285],"evaluation.":[290]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}