{"id":"https://openalex.org/W4382201625","doi":"https://doi.org/10.1145/3582768.3582802","title":"CWITR: A Corpus for Automatic Complex Word Identification in Turkish Texts","display_name":"CWITR: A Corpus for Automatic Complex Word Identification in Turkish Texts","publication_year":2022,"publication_date":"2022-12-16","ids":{"openalex":"https://openalex.org/W4382201625","doi":"https://doi.org/10.1145/3582768.3582802"},"language":"en","primary_location":{"id":"doi:10.1145/3582768.3582802","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582768.3582802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th 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/A5052706760","display_name":"Bahar \u0130lgen","orcid":"https://orcid.org/0000-0001-5725-0850"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bahar Ilgen","raw_affiliation_strings":["Language Technology Group, Department of Informatics, University of Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5725-0850","affiliations":[{"raw_affiliation_string":"Language Technology Group, Department of Informatics, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":["Language Technology Group, Department of Informatics, University of Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8449-9624","affiliations":[{"raw_affiliation_string":"Language Technology Group, Department of Informatics, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052706760"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":0.1387,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58695203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":1.0,"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/T13629","display_name":"Text Readability and Simplification","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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":0.9456999897956848,"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":0.807781457901001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.806729793548584},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6810575723648071},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6732783317565918},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6644710302352905},{"id":"https://openalex.org/keywords/word-identification","display_name":"Word identification","score":0.6585474610328674},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5924980640411377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5794710516929626},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.533584475517273},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20357313752174377},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.10288164019584656},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05325502157211304}],"concepts":[{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.807781457901001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806729793548584},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6810575723648071},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6732783317565918},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6644710302352905},{"id":"https://openalex.org/C2994428975","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word identification","level":4,"score":0.6585474610328674},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5924980640411377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5794710516929626},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.533584475517273},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20357313752174377},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.10288164019584656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05325502157211304},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3582768.3582802","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582768.3582802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2004316800","https://openalex.org/W2033777670","https://openalex.org/W2036367260","https://openalex.org/W2063490579","https://openalex.org/W2160724766","https://openalex.org/W2565470033","https://openalex.org/W2770960740","https://openalex.org/W2771576526","https://openalex.org/W2771976988","https://openalex.org/W2805222462","https://openalex.org/W3135809019","https://openalex.org/W3183368628","https://openalex.org/W6825768580"],"related_works":["https://openalex.org/W1992616322","https://openalex.org/W2036873286","https://openalex.org/W2408487574","https://openalex.org/W4283746496","https://openalex.org/W2364032347","https://openalex.org/W438210688","https://openalex.org/W3032649931","https://openalex.org/W2413876267","https://openalex.org/W3012475325","https://openalex.org/W2114272857"],"abstract_inverted_index":{"The":[0,25],"Complex":[1],"Word":[2],"Identification":[3],"(CWI)":[4],"task":[5,26,67],"aims":[6],"to":[7,10,42],"provide":[8],"support":[9],"resolve":[11],"accessibility":[12],"barriers":[13],"for":[14,99,104],"people":[15],"who":[16],"experience":[17],"difficulties":[18],"with":[19,29],"cognitive,":[20],"language,":[21],"and":[22,32,40,91,101,113],"learning":[23],"disabilities.":[24],"is":[27],"concerned":[28],"the":[30,55,65],"detection":[31],"identification":[33],"of":[34,57,88,95,106],"complex":[35,89,112],"words":[36,93,115],"that":[37],"are":[38],"unusual":[39],"difficult":[41],"understand":[43],"by":[44,68,72],"certain":[45],"target":[46],"groups.":[47],"CWI":[48,66,76,85],"systems":[49],"have":[50],"a":[51,74,83],"large":[52],"impact":[53],"on":[54,109],"output":[56],"Text":[58],"Simplification":[59],"(TS)":[60],"systems.":[61],"This":[62],"paper":[63],"revisits":[64],"extending":[69],"available":[70],"datasets":[71],"creating":[73],"new":[75,84],"corpus.":[77],"In":[78],"this":[79],"study,":[80],"we":[81],"collect":[82],"dataset":[86],"(CWITR)":[87],"single":[90],"multi-token":[92],"consisting":[94],"different":[96],"text":[97],"genres":[98],"Turkish":[100],"prepare":[102],"it":[103],"investigation":[105],"computational":[107],"methods":[108],"discrimination":[110],"between":[111],"non-complex":[114],"forms.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}