{"id":"https://openalex.org/W7139920564","doi":"https://doi.org/10.1016/j.procs.2026.01.041","title":"TurkLink: A Morphologically-Aware and Syntactically Enriched Corpus for Entity Linking in Turkish","display_name":"TurkLink: A Morphologically-Aware and Syntactically Enriched Corpus for Entity Linking in Turkish","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139920564","doi":"https://doi.org/10.1016/j.procs.2026.01.041"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.01.041","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.041","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2026.01.041","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130238991","display_name":"Yusuf Akda\u015f","orcid":null},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Yusuf Akda\u015f","raw_affiliation_strings":["Computer Engineering Dept., Graduate School, Istanbul Technical University, \u0130stanbul, 34467, T\u00fcrkiye"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Dept., Graduate School, Istanbul Technical University, \u0130stanbul, 34467, T\u00fcrkiye","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086282318","display_name":"A. C\u00fcneyd Tantu\u011f","orcid":"https://orcid.org/0000-0003-0524-3397"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ahmet C\u00fcneyd Tantu\u011f","raw_affiliation_strings":["Artificial Intelligence and Data Engineering Dept., Faculty of Computer and Informatics, Istanbul Technical University, \u0130stanbul, 34467, T\u00fcrkiye"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Data Engineering Dept., Faculty of Computer and Informatics, Istanbul Technical University, \u0130stanbul, 34467, T\u00fcrkiye","institution_ids":["https://openalex.org/I48912391"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5130238991"],"corresponding_institution_ids":["https://openalex.org/I48912391"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9307438,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"275","issue":null,"first_page":"333","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.31360000371932983,"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":0.31360000371932983,"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":0.25690001249313354,"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/T13629","display_name":"Text Readability and Simplification","score":0.0949999988079071,"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/turkish","display_name":"Turkish","score":0.8123999834060669},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.25929999351501465},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.23749999701976776},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.2257000058889389}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9077000021934509},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.8123999834060669},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6855999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050999760627747},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3472000062465668},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.24400000274181366},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.23749999701976776},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.2257000058889389},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.22470000386238098}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.01.041","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.041","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2026.01.041","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.041","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2004316800","https://openalex.org/W2091950909","https://openalex.org/W2122865749","https://openalex.org/W2144578941","https://openalex.org/W2250865411","https://openalex.org/W2763587528","https://openalex.org/W3100843744","https://openalex.org/W3214173179","https://openalex.org/W4287887705","https://openalex.org/W4293863334"],"related_works":[],"abstract_inverted_index":{"Entity":[0],"linking":[1,6,71],"is":[2,31,81,190],"the":[3,23,32,109,127,133,162,181,223],"task":[4],"of":[5,34,79,108,118,132,141,170],"textual":[7],"mentions":[8],"to":[9,200],"entities":[10,124],"in":[11,28],"a":[12,35,47,116,145,153,167,203],"knowledge":[13],"graph":[14],"like":[15,21],"Wikidata.":[16,54],"For":[17],"morphologically":[18],"rich":[19],"languages":[20],"Turkish,":[22],"primary":[24],"bottleneck":[25],"for":[26,68,103,206],"research":[27,208],"this":[29,42],"area":[30],"lack":[33],"large-scale,":[36],"publicly":[37],"available":[38],"corpus.":[39],"To":[40,136],"address":[41],"issue,":[43],"we":[44],"introduce":[45],"TurkLink,":[46],"new":[48],"corpus":[49,111,215],"based":[50],"on":[51,156,161,172,180,209],"Wikipedia":[52],"and":[53,61,65,72,97,121,125,129,177,184,196,216],"This":[55],"resource":[56,205],"comprises":[57,115],"approximately":[58],"590,000":[59],"articles":[60],"97":[62],"million":[63],"tokens":[64],"contains":[66],"annotations":[67],"both":[69,119],"entity":[70,74,163,211],"named":[73],"recognition.":[75],"A":[76],"distinguishing":[77],"feature":[78],"TurkLink":[80,157,189],"its":[82,142],"linguistic":[83],"enrichment,":[84],"added":[85],"via":[86],"an":[87,138],"existing":[88],"NLP":[89],"tool,":[90],"which":[91],"includes":[92],"part-of-speech":[93],"tags,":[94],"morphological":[95,130],"analyses,":[96],"complete":[98,214],"syntactic":[99],"dependency":[100],"parse":[101],"trees":[102],"every":[104],"sentence.":[105],"Our":[106],"analysis":[107],"Turklink":[110],"reveals":[112],"that":[113,152],"it":[114],"mix":[117],"lesser-known":[120],"more":[122],"common":[123],"reflects":[126],"structural":[128],"challenges":[131],"Turkish":[134,187,210],"language.":[135],"provide":[137],"initial":[139],"indication":[140],"utility":[143],"as":[144,202],"training":[146],"resource,":[147],"our":[148,173],"preliminary":[149],"experiment":[150],"shows":[151],"model":[154],"trained":[155],"achieves":[158],"promising":[159],"results":[160],"disambiguation":[164],"sub-task,":[165],"including":[166],"micro":[168],"F1-score":[169],"0.9414":[171],"internal":[174],"test":[175,197],"set":[176],"over":[178],"0.90":[179],"Mewsli-9":[182],"[3]":[183],"Mewsli-X":[185],"[15]":[186],"subsets.":[188],"released":[191],"with":[192],"standard":[193],"training,":[194],"validation,":[195],"splits,":[198],"aiming":[199],"serve":[201],"foundational":[204],"future":[207],"linking.":[212],"The":[213],"all":[217],"associated":[218],"resources":[219],"are":[220],"accessible":[221],"under":[222],"CC":[224],"BY-SA":[225],"4.0":[226],"license":[227],"at":[228],"https://huggingface.co/datasets/yakdas/turklink-corpus":[229]},"counts_by_year":[],"updated_date":"2026-03-22T06:25:25.174409","created_date":"2026-03-21T00:00:00"}
