{"id":"https://openalex.org/W3009487227","doi":"https://doi.org/10.1109/icdmw48858.2019.9024753","title":"Analyzing Similarities between Word Frequency Distributions of Various Corpora to Find Effective Features for Complex Word Identification","display_name":"Analyzing Similarities between Word Frequency Distributions of Various Corpora to Find Effective Features for Complex Word Identification","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3009487227","doi":"https://doi.org/10.1109/icdmw48858.2019.9024753","mag":"3009487227"},"language":"en","primary_location":{"id":"doi:10.1109/icdmw48858.2019.9024753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw48858.2019.9024753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5007171156","display_name":"Yo Ehara","orcid":"https://orcid.org/0000-0001-9314-4617"},"institutions":[{"id":"https://openalex.org/I85140907","display_name":"Shizuoka Institute of Science and Technology","ror":"https://ror.org/00vq1d511","country_code":"JP","type":"education","lineage":["https://openalex.org/I85140907"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yo Ehara","raw_affiliation_strings":["Department of Computer Science\nShizuoka Institute of Science and Technology\n2200-2, Toyosawa, Fukuroi, Shizuoka, Japan. 437-8555"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science\nShizuoka Institute of Science and Technology\n2200-2, Toyosawa, Fukuroi, Shizuoka, Japan. 437-8555","institution_ids":["https://openalex.org/I85140907"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007171156"],"corresponding_institution_ids":["https://openalex.org/I85140907"],"apc_list":null,"apc_paid":null,"fwci":0.1093,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.45779839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2019","issue":null,"first_page":"1","last_page":"4"},"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":0.998199999332428,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.8210231065750122},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.781052827835083},{"id":"https://openalex.org/keywords/word-identification","display_name":"Word identification","score":0.7631617784500122},{"id":"https://openalex.org/keywords/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.7390569448471069},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6563122272491455},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6481510400772095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5992504358291626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43339312076568604},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.24472787976264954},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17100873589515686}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8210231065750122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781052827835083},{"id":"https://openalex.org/C2994428975","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word identification","level":4,"score":0.7631617784500122},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.7390569448471069},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6563122272491455},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6481510400772095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5992504358291626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43339312076568604},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.24472787976264954},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17100873589515686},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdmw48858.2019.9024753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw48858.2019.9024753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},{"id":"mag:3041953799","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002251135379544","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W195533127","https://openalex.org/W1499253590","https://openalex.org/W1525283044","https://openalex.org/W1964698778","https://openalex.org/W1985672254","https://openalex.org/W2037170747","https://openalex.org/W2044688197","https://openalex.org/W2047328202","https://openalex.org/W2124926790","https://openalex.org/W2140785772","https://openalex.org/W2144950812","https://openalex.org/W2162614464","https://openalex.org/W2169294309","https://openalex.org/W2250340570","https://openalex.org/W2250418535","https://openalex.org/W2473989358","https://openalex.org/W2577885215","https://openalex.org/W2579059440","https://openalex.org/W2756654724","https://openalex.org/W2805197999","https://openalex.org/W2807251235","https://openalex.org/W2827279372","https://openalex.org/W2838983983","https://openalex.org/W2939860970","https://openalex.org/W2963510222","https://openalex.org/W3158183629"],"related_works":["https://openalex.org/W656863500","https://openalex.org/W2408487574","https://openalex.org/W1508636238","https://openalex.org/W2010892440","https://openalex.org/W2369443301","https://openalex.org/W1983533318","https://openalex.org/W3009487227","https://openalex.org/W1990034193","https://openalex.org/W2602143361","https://openalex.org/W2475268295"],"abstract_inverted_index":{"Complex":[0],"word":[1,58,65,140],"identification":[2,43],"(CWI)":[3],"is":[4],"a":[5,18,33,62,75,84,131,157],"fundamental":[6],"educational":[7],"natural":[8],"language":[9],"processing":[10],"(NLP)":[11],"task":[12,160],"that":[13],"identifies":[14],"complex":[15,45],"words":[16],"in":[17,22,41,55,150],"text":[19,27],"for":[20,114],"use":[21],"many":[23],"further":[24],"applications,":[25],"including":[26],"simplification.":[28],"Word":[29],"frequency":[30,59,66,141],"features":[31,60,67],"from":[32,61,68],"general":[34,63,104],"corpus":[35,78,86],"were":[36,173],"known":[37],"to":[38,125,130],"be":[39,126,148],"effective":[40,115,122,177],"the":[42,92,98,112,139,167],"of":[44,71,103,121,143,171],"words.":[46],"Recent":[47],"studies":[48],"have":[49],"independently":[50],"discovered":[51],"that,":[52],"when":[53],"used":[54],"combination":[56,102],"with":[57],"corpus,":[64],"some":[69],"types":[70,120],"non-general":[72,106],"corpora,":[73,145],"namely,":[74],"movie":[76],"subtitle":[77],"(Peatzold":[79],"and":[80,83,88,105,118],"Specia,":[81],"2016)":[82],"learner":[85],"(Kajiwara":[87],"Komachi,":[89],"2018),":[90],"improved":[91,108],"CWI":[93,158],"accuracy.":[94],"As":[95],"long":[96],"as":[97],"reason":[99],"why":[100,166],"this":[101,134],"corpora":[107,116,123,172,178],"accuracy":[109],"remained":[110],"unclear,":[111],"search":[113],"combinations":[117,170],"other":[119],"had":[124],"exhaustive.":[127],"To":[128],"contribute":[129],"non-exhaustive":[132],"search,":[133],"study":[135],"analyzes":[136],"similarities":[137],"among":[138],"distributions":[142],"various":[144],"which":[146],"can":[147],"conducted":[149],"an":[151],"unsupervised":[152],"manner.":[153],"In":[154],"experiments":[155],"using":[156],"shared":[159],"dataset,":[161],"our":[162],"method":[163],"successfully":[164],"explains":[165],"previously":[168],"reported":[169],"effective,":[174],"while":[175],"finding":[176],"combinations.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}