{"id":"https://openalex.org/W2977788613","doi":"https://doi.org/10.13053/cys-23-3-3271","title":"Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection","display_name":"Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection","publication_year":2019,"publication_date":"2019-10-07","ids":{"openalex":"https://openalex.org/W2977788613","doi":"https://doi.org/10.13053/cys-23-3-3271","mag":"2977788613"},"language":"es","primary_location":{"id":"doi:10.13053/cys-23-3-3271","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-23-3-3271","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-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/A5005531754","display_name":"Masahiro Kaneko","orcid":"https://orcid.org/0000-0002-5117-5447"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Masahiro Kaneko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061931124","display_name":"Mamoru Komachi","orcid":"https://orcid.org/0000-0003-1166-1739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mamoru Komachi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005531754"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9602,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.89850178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"23","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9962000250816345,"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":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.8280225992202759},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6373149752616882},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6056787967681885},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5746639966964722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5594562292098999},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5437849760055542},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5345795154571533},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.514579713344574},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4753111004829407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280225992202759},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6373149752616882},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6056787967681885},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5746639966964722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594562292098999},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5437849760055542},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5345795154571533},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.514579713344574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4753111004829407},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.13053/cys-23-3-3271","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-23-3-3271","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"It":[0],"is":[1,44],"known":[2],"that":[3,103,157,181],"a":[4,31,98,167,176,179],"deep":[5],"neural":[6],"networkmodel":[7],"pre-trained":[8,88],"with":[9],"large-scale":[10],"data":[11],"greatly":[12],"improves":[13],"the":[14,26,38,41,71,79,105,119,130,134,184],"accuracy":[15],"of":[16,40,73,133,152,170],"various":[17],"tasks,":[18,128],"especially":[19],"when":[20],"there":[21],"are":[22],"resource":[23],"constraints.":[24],"However,":[25],"information":[27,75,171],"needed":[28],"to":[29,49,57,92],"solve":[30],"given":[32],"task":[33],"can":[34,165],"vary,":[35],"and":[36,146],"simplyusing":[37],"output":[39],"final":[42,80,185],"layer":[43,81],"not":[45,62,76],"necessarily":[46],"sufficient.":[47],"Moreover,":[48],"our":[50,163],"knowledge,":[51],"exploiting":[52],"large":[53],"language":[54,89],"representation":[55,90],"models":[56],"detect":[58,93],"grammatical":[59,94,125],"errors":[60],"has":[61],"yet":[63],"been":[64],"studied.":[65],"In":[66],"this":[67],"work,":[68],"we":[69],"investigate":[70],"effect":[72],"utilizing":[74],"only":[77,183],"from":[78,84,112],"but":[82],"also":[83,155],"intermediate":[85],"layers":[86,107],"ofa":[87],"model":[91,102,164,180],"errors.":[95],"We":[96,154],"propose":[97],"multi-head":[99,160],"multi-layer":[100,161],"attention":[101],"determines":[104],"appropriate":[106],"in":[108,150,175],"Bidirectional":[109],"Encoder":[110],"Representation":[111],"Transformers":[113],"(BERT).":[114],"The":[115],"proposed":[116],"method":[117,136],"achieved":[118],"best":[120],"scoreson":[121],"three":[122],"datasets":[123],"for":[124,172],"error":[126],"detection":[127],"outperforming":[129],"current":[131],"state":[132],"art":[135],"by":[137,158],"6.0":[138],"points":[139,143],"on":[140,144],"FCE,":[141],"8.2":[142],"CoNLL14,":[145],"12.2":[147],"pointson":[148],"JFLEG":[149],"terms":[151],"F0.5.":[153],"demonstrate":[156],"using":[159],"attention,":[162],"exploit":[166],"broader":[168],"range":[169],"each":[173],"token":[174],"sentence":[177],"than":[178],"uses":[182],"layer\u2019s":[186],"information.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}