{"id":"https://openalex.org/W2805222462","doi":"https://doi.org/10.18653/v1/w18-0538","title":"Complex Word Identification: Convolutional Neural Network vs. Feature Engineering","display_name":"Complex Word Identification: Convolutional Neural Network vs. Feature Engineering","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2805222462","doi":"https://doi.org/10.18653/v1/w18-0538","mag":"2805222462"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-0538","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-0538","pdf_url":"https://www.aclweb.org/anthology/W18-0538.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth Workshop on Innovative Use of NLP for\n          Building Educational Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-0538.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063612283","display_name":"Segun Taofeek Aroyehun","orcid":"https://orcid.org/0000-0002-2571-3731"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Segun Taofeek Aroyehun","raw_affiliation_strings":["CIC, Instituto Polit\u00e9cnico Nacional Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"CIC, Instituto Polit\u00e9cnico Nacional Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088734006","display_name":"Jason Angel","orcid":"https://orcid.org/0000-0002-7991-1979"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jason Angel","raw_affiliation_strings":["CIC, Instituto Politcnico Nacional Mexico City, Mexico","CIC, Instituto Polit\u00e9cnico Nacional Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"CIC, Instituto Politcnico Nacional Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]},{"raw_affiliation_string":"CIC, Instituto Polit\u00e9cnico Nacional Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011259890","display_name":"Daniel Alejandro P\u00e9rez Alvarez","orcid":"https://orcid.org/0000-0001-9624-1324"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Daniel Alejandro P\u00e9rez Alvarez","raw_affiliation_strings":["CIC, Instituto Politcnico Nacional Mexico City, Mexico","CIC, Instituto Polit\u00e9cnico Nacional Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"CIC, Instituto Politcnico Nacional Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]},{"raw_affiliation_string":"CIC, Instituto Polit\u00e9cnico Nacional Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049701126","display_name":"Alexander Gelbukh","orcid":"https://orcid.org/0000-0001-7845-9039"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Alexander Gelbukh","raw_affiliation_strings":["CIC, Instituto Politcnico Nacional Mexico City, Mexico","CIC, Instituto Polit\u00e9cnico Nacional Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"CIC, Instituto Politcnico Nacional Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]},{"raw_affiliation_string":"CIC, Instituto Polit\u00e9cnico Nacional Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063612283"],"corresponding_institution_ids":["https://openalex.org/I59361560"],"apc_list":null,"apc_paid":null,"fwci":1.8616,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88980519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"322","last_page":"327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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":0.9937000274658203,"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/feature-engineering","display_name":"Feature engineering","score":0.808139443397522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8032530546188354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7254893183708191},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.668830394744873},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6320803761482239},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6076454520225525},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5832770466804504},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5829365253448486},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5764220356941223},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5655893087387085},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5554884672164917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5392206311225891},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49645739793777466},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4838825464248657},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.4516914188861847},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4333064556121826},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4275832176208496},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3402423858642578},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08865609765052795},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06612503528594971},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0654173195362091}],"concepts":[{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.808139443397522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032530546188354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7254893183708191},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.668830394744873},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6320803761482239},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6076454520225525},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5832770466804504},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5829365253448486},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5764220356941223},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5655893087387085},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5554884672164917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5392206311225891},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49645739793777466},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4838825464248657},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.4516914188861847},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4333064556121826},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4275832176208496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3402423858642578},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08865609765052795},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06612503528594971},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0654173195362091},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-0538","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-0538","pdf_url":"https://www.aclweb.org/anthology/W18-0538.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth Workshop on Innovative Use of NLP for\n          Building Educational Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-0538","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-0538","pdf_url":"https://www.aclweb.org/anthology/W18-0538.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth Workshop on Innovative Use of NLP for\n          Building Educational Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8427600393","display_name":null,"funder_award_id":"SIP-2018","funder_id":"https://openalex.org/F4320321694","funder_display_name":"Instituto Polit\u00e9cnico Nacional"}],"funders":[{"id":"https://openalex.org/F4320321694","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34"},{"id":"https://openalex.org/F4320321739","display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/059ex5q34"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2805222462.pdf","grobid_xml":"https://content.openalex.org/works/W2805222462.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1832693441","https://openalex.org/W2049434052","https://openalex.org/W2095705004","https://openalex.org/W2101234009","https://openalex.org/W2250889812","https://openalex.org/W2294860948","https://openalex.org/W2460985275","https://openalex.org/W2463877837","https://openalex.org/W2464252445","https://openalex.org/W2471229275","https://openalex.org/W2473360228","https://openalex.org/W2473989358","https://openalex.org/W2557283755","https://openalex.org/W2771780353","https://openalex.org/W2773955291","https://openalex.org/W2950577311","https://openalex.org/W2963510222","https://openalex.org/W2963667932","https://openalex.org/W2964174591","https://openalex.org/W4297801177"],"related_works":["https://openalex.org/W2030816003","https://openalex.org/W4239992647","https://openalex.org/W2150013480","https://openalex.org/W1554458299","https://openalex.org/W81423522","https://openalex.org/W1509860481","https://openalex.org/W2488264085","https://openalex.org/W2076325756","https://openalex.org/W2965782936","https://openalex.org/W2805222462"],"abstract_inverted_index":{"We":[0,64],"describe":[1],"the":[2,10,35,60,66,69,74,81,96,99,104,120],"systems":[3,85,91],"of":[4,37,68,95],"NLP-CIC":[5],"team":[6],"that":[7],"participated":[8],"in":[9,29,80],"Complex":[11],"Word":[12],"Identification":[13],"(CWI)":[14],"2018":[15],"shared":[16,19],"task.":[17],"The":[18],"task":[20],"aimed":[21],"to":[22,43],"benchmark":[23],"approaches":[24,55],"for":[25],"identifying":[26],"complex":[27],"words":[28],"English":[30,61],"and":[31,49],"other":[32],"languages":[33],"from":[34],"perspective":[36],"non-native":[38],"speakers.":[39],"Our":[40,84],"goal":[41],"is":[42,117],"compare":[44],"two":[45],"approaches:":[46],"feature":[47],"engineering":[48],"a":[50],"deep":[51,76],"neural":[52,77],"network.":[53],"Both":[54],"achieved":[56,86],"comparable":[57],"performance":[58],"on":[59,103,108,112],"test":[62,105,110],"set.":[63],"demonstrated":[65],"flexibility":[67],"deeplearning":[70],"approach":[71],"by":[72],"using":[73],"same":[75],"network":[78],"setup":[79],"Spanish":[82],"track.":[83],"competitive":[87],"results:":[88],"all":[89],"our":[90,114],"were":[92],"within":[93],"0.01":[94],"system":[97,116],"with":[98],"best":[100,115,121],"macro-F1":[101,122],"score":[102],"sets":[106],"except":[107],"Wikipedia":[109],"set,":[111],"which":[113],"0.04":[118],"below":[119],"score.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
