{"id":"https://openalex.org/W4224909334","doi":"https://doi.org/10.1017/s1351324922000171","title":"A survey of methods for revealing and overcoming weaknesses of data-driven Natural Language Understanding","display_name":"A survey of methods for revealing and overcoming weaknesses of data-driven Natural Language Understanding","publication_year":2022,"publication_date":"2022-04-22","ids":{"openalex":"https://openalex.org/W4224909334","doi":"https://doi.org/10.1017/s1351324922000171"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324922000171","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324922000171","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/BC8EBADC7D8E5CFC67FC1FE5958E13CC/S1351324922000171a.pdf/div-class-title-a-survey-of-methods-for-revealing-and-overcoming-weaknesses-of-data-driven-natural-language-understanding-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/BC8EBADC7D8E5CFC67FC1FE5958E13CC/S1351324922000171a.pdf/div-class-title-a-survey-of-methods-for-revealing-and-overcoming-weaknesses-of-data-driven-natural-language-understanding-div.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037328707","display_name":"Viktor Schlegel","orcid":"https://orcid.org/0000-0002-6391-2950"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Viktor Schlegel","raw_affiliation_strings":["Department of Computer Science, University of Manchester, Manchester M13 9PL, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester, Manchester M13 9PL, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005912060","display_name":"Goran Nenadi\u0107","orcid":"https://orcid.org/0000-0003-0795-5363"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Goran Nenadic","raw_affiliation_strings":["Department of Computer Science, University of Manchester, Manchester M13 9PL, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester, Manchester M13 9PL, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050960711","display_name":"Riza Batista-Navarro","orcid":"https://orcid.org/0000-0001-6693-7531"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Riza Batista-Navarro","raw_affiliation_strings":["Department of Computer Science, University of Manchester, Manchester M13 9PL, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester, Manchester M13 9PL, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037328707"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":0.4025,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57668654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"29","issue":"1","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9990000128746033,"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":0.9983000159263611,"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":0.847035825252533},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.8174247741699219},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6064504384994507},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5921224355697632},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.5764376521110535},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.536446213722229},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.519836962223053},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.447922945022583},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4410393238067627},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4325181543827057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35510939359664917},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0708734393119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847035825252533},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.8174247741699219},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6064504384994507},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5921224355697632},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.5764376521110535},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.536446213722229},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.519836962223053},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.447922945022583},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4410393238067627},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4325181543827057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35510939359664917},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0708734393119812},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324922000171","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324922000171","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/BC8EBADC7D8E5CFC67FC1FE5958E13CC/S1351324922000171a.pdf/div-class-title-a-survey-of-methods-for-revealing-and-overcoming-weaknesses-of-data-driven-natural-language-understanding-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/b53babe5-1dfd-4ba7-acc8-26df5d9a4f6c","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/b53babe5-1dfd-4ba7-acc8-26df5d9a4f6c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Schlegel, V, Nenadic, G & Batista-Navarro, R 2023, 'A survey of methods for revealing and overcoming weaknesses of data-driven Natural Language Understanding', Natural Language Engineering, vol. 29, no. 1, pp. 1-31. https://doi.org/10.1017/S1351324922000171","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1017/s1351324922000171","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324922000171","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/BC8EBADC7D8E5CFC67FC1FE5958E13CC/S1351324922000171a.pdf/div-class-title-a-survey-of-methods-for-revealing-and-overcoming-weaknesses-of-data-driven-natural-language-understanding-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306122","display_name":"Institute of Museum and Library Services","ror":"https://ror.org/030prv062"},{"id":"https://openalex.org/F4320337253","display_name":"Instituto de Ciencias del Mar y Limnolog\u00eda, Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4224909334.pdf","grobid_xml":"https://content.openalex.org/works/W4224909334.grobid-xml"},"referenced_works_count":171,"referenced_works":["https://openalex.org/W1840435438","https://openalex.org/W2133564696","https://openalex.org/W2145755360","https://openalex.org/W2251818205","https://openalex.org/W2251919380","https://openalex.org/W2295405869","https://openalex.org/W2466175319","https://openalex.org/W2551396370","https://openalex.org/W2604832008","https://openalex.org/W2739505524","https://openalex.org/W2739810148","https://openalex.org/W2742122443","https://openalex.org/W2788292930","https://openalex.org/W2789352267","https://openalex.org/W2798617936","https://openalex.org/W2798665661","https://openalex.org/W2799007037","https://openalex.org/W2799424953","https://openalex.org/W2805083708","https://openalex.org/W2843921263","https://openalex.org/W2888302696","https://openalex.org/W2888491130","https://openalex.org/W2889453388","https://openalex.org/W2889468083","https://openalex.org/W2889787757","https://openalex.org/W2890894339","https://openalex.org/W2891113091","https://openalex.org/W2892354372","https://openalex.org/W2896457183","https://openalex.org/W2912924812","https://openalex.org/W2923014074","https://openalex.org/W2927622107","https://openalex.org/W2942128719","https://openalex.org/W2946609015","https://openalex.org/W2946659172","https://openalex.org/W2949818215","https://openalex.org/W2949911172","https://openalex.org/W2950470622","https://openalex.org/W2951181836","https://openalex.org/W2951286828","https://openalex.org/W2951328433","https://openalex.org/W2951365061","https://openalex.org/W2951568144","https://openalex.org/W2951873305","https://openalex.org/W2952984539","https://openalex.org/W2953039212","https://openalex.org/W2953163841","https://openalex.org/W2954194820","https://openalex.org/W2955436390","https://openalex.org/W2962727366","https://openalex.org/W2962736243","https://openalex.org/W2962809918","https://openalex.org/W2962842748","https://openalex.org/W2963015836","https://openalex.org/W2963159690","https://openalex.org/W2963159735","https://openalex.org/W2963249435","https://openalex.org/W2963368301","https://openalex.org/W2963538407","https://openalex.org/W2963542100","https://openalex.org/W2963615251","https://openalex.org/W2963748441","https://openalex.org/W2963783970","https://openalex.org/W2963797754","https://openalex.org/W2963846996","https://openalex.org/W2963866616","https://openalex.org/W2963903928","https://openalex.org/W2963957386","https://openalex.org/W2963961878","https://openalex.org/W2963969878","https://openalex.org/W2963983586","https://openalex.org/W2964032269","https://openalex.org/W2964044490","https://openalex.org/W2964150944","https://openalex.org/W2970019270","https://openalex.org/W2970078867","https://openalex.org/W2970116058","https://openalex.org/W2970243238","https://openalex.org/W2970379526","https://openalex.org/W2970482702","https://openalex.org/W2970530230","https://openalex.org/W2970780738","https://openalex.org/W2970819455","https://openalex.org/W2970946372","https://openalex.org/W2971089712","https://openalex.org/W2971107062","https://openalex.org/W2971236147","https://openalex.org/W2975059944","https://openalex.org/W2977235550","https://openalex.org/W2982756474","https://openalex.org/W2982944182","https://openalex.org/W2983984338","https://openalex.org/W2984178847","https://openalex.org/W2984256198","https://openalex.org/W2984978596","https://openalex.org/W2985347336","https://openalex.org/W2985964562","https://openalex.org/W2987553933","https://openalex.org/W2987660687","https://openalex.org/W2988421999","https://openalex.org/W2991356836","https://openalex.org/W2991497298","https://openalex.org/W2996164352","https://openalex.org/W2996908057","https://openalex.org/W2997616454","https://openalex.org/W2997645422","https://openalex.org/W2997789497","https://openalex.org/W2998072062","https://openalex.org/W2998099211","https://openalex.org/W2998107946","https://openalex.org/W3009380369","https://openalex.org/W3011013442","https://openalex.org/W3011654523","https://openalex.org/W3013360982","https://openalex.org/W3013520104","https://openalex.org/W3015001695","https://openalex.org/W3016049383","https://openalex.org/W3021606318","https://openalex.org/W3022116759","https://openalex.org/W3025458843","https://openalex.org/W3029617638","https://openalex.org/W3030707950","https://openalex.org/W3034475796","https://openalex.org/W3034584102","https://openalex.org/W3034831508","https://openalex.org/W3034850762","https://openalex.org/W3035139434","https://openalex.org/W3035267217","https://openalex.org/W3035352537","https://openalex.org/W3035438620","https://openalex.org/W3035507081","https://openalex.org/W3035599593","https://openalex.org/W3035718362","https://openalex.org/W3037211561","https://openalex.org/W3037869352","https://openalex.org/W3045462440","https://openalex.org/W3049481998","https://openalex.org/W3089102176","https://openalex.org/W3095992020","https://openalex.org/W3099080236","https://openalex.org/W3099246072","https://openalex.org/W3100378811","https://openalex.org/W3100894295","https://openalex.org/W3103291112","https://openalex.org/W3103585424","https://openalex.org/W3103621845","https://openalex.org/W3103873238","https://openalex.org/W3104178968","https://openalex.org/W3105302490","https://openalex.org/W3105928338","https://openalex.org/W3106156541","https://openalex.org/W3106544837","https://openalex.org/W3155728828","https://openalex.org/W3162922479","https://openalex.org/W3169223343","https://openalex.org/W3170700068","https://openalex.org/W3172642864","https://openalex.org/W3175508917","https://openalex.org/W3177028045","https://openalex.org/W3181414820","https://openalex.org/W3204222276","https://openalex.org/W4211148418","https://openalex.org/W4288089799","https://openalex.org/W4289303350","https://openalex.org/W6632455782","https://openalex.org/W6637162671","https://openalex.org/W6739901393","https://openalex.org/W6769627184","https://openalex.org/W6771748797","https://openalex.org/W6775798855","https://openalex.org/W6780484765"],"related_works":["https://openalex.org/W1599620240","https://openalex.org/W3082463427","https://openalex.org/W2886693075","https://openalex.org/W2836780890","https://openalex.org/W1542956019","https://openalex.org/W2977842567","https://openalex.org/W2897503929","https://openalex.org/W3118511871","https://openalex.org/W2315370695","https://openalex.org/W2978955179"],"abstract_inverted_index":{"Abstract":[0],"Recent":[1],"years":[2],"have":[3],"seen":[4],"a":[5,87,102],"growing":[6],"number":[7],"of":[8,25,51,89,117,124,140],"publications":[9],"that":[10,37,98],"analyse":[11],"Natural":[12],"Language":[13],"Understanding":[14],"(NLU)":[15],"datasets":[16,30,63,110],"for":[17,74,91,105],"superficial":[18],"cues,":[19],"whether":[20],"they":[21,33],"undermine":[22],"the":[23,26,52,65,75,82,113,138],"complexity":[24],"tasks":[27],"underlying":[28],"those":[29,35,72,129],"and":[31,40,62,64,70,80,84,115],"how":[32],"impact":[34],"models":[36,61],"are":[38],"optimised":[39],"evaluated":[41],"on":[42],"this":[43],"data.":[44],"This":[45],"structured":[46],"survey":[47],"provides":[48],"an":[49],"overview":[50],"evolving":[53],"research":[54,94],"area":[55],"by":[56],"categorising":[57],"reported":[58],"weaknesses":[59,73],"in":[60],"methods":[66],"proposed":[67],"to":[68,111,120,135,145],"reveal":[69],"alleviate":[71],"English":[76],"language.":[77],"We":[78,96],"summarise":[79],"discuss":[81],"findings":[83],"conclude":[85],"with":[86,143],"set":[88],"recommendations":[90],"possible":[92],"future":[93],"directions.":[95],"hope":[97],"it":[99],"will":[100],"be":[101],"useful":[103],"resource":[104],"researchers":[106],"who":[107,130],"propose":[108,131],"new":[109],"assess":[112],"suitability":[114],"quality":[116],"their":[118,141,146],"data":[119],"evaluate":[121],"various":[122],"phenomena":[123],"interest,":[125],"as":[126,128],"well":[127],"novel":[132],"NLU":[133],"approaches,":[134],"further":[136],"understand":[137],"implications":[139],"improvements":[142],"respect":[144],"model\u2019s":[147],"acquired":[148],"capabilities.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}