{"id":"https://openalex.org/W3012813596","doi":"https://doi.org/10.1017/s1351324921000127","title":"TNT-KID: Transformer-based neural tagger for keyword identification","display_name":"TNT-KID: Transformer-based neural tagger for keyword identification","publication_year":2021,"publication_date":"2021-06-10","ids":{"openalex":"https://openalex.org/W3012813596","doi":"https://doi.org/10.1017/s1351324921000127","mag":"3012813596"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324921000127","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324921000127","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A41C8B12C1F3F4F02BF839FCAFA1A695/S1351324921000127a.pdf/div-class-title-tnt-kid-transformer-based-neural-tagger-for-keyword-identification-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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A41C8B12C1F3F4F02BF839FCAFA1A695/S1351324921000127a.pdf/div-class-title-tnt-kid-transformer-based-neural-tagger-for-keyword-identification-div.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000491019","display_name":"Matej Martinc","orcid":"https://orcid.org/0000-0002-7384-8112"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]},{"id":"https://openalex.org/I4210113529","display_name":"Jo\u017eef Stefan International Postgraduate School","ror":"https://ror.org/01hdkb925","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210113529"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Matej Martinc","raw_affiliation_strings":["Joef Stefan Institute, Department of Knowledge Technologies, Jamova 39, 1000 Ljubljana, Slovenia and","Joef Stefan International Postgraduate School, Department of Knowledge Technologies, Jamova 39, 1000 Ljubljana, Slovenia","Jo\u017eef Stefan Institute"],"raw_orcid":"https://orcid.org/0000-0002-7384-8112","affiliations":[{"raw_affiliation_string":"Joef Stefan Institute, Department of Knowledge Technologies, Jamova 39, 1000 Ljubljana, Slovenia and","institution_ids":["https://openalex.org/I3006985408"]},{"raw_affiliation_string":"Joef Stefan International Postgraduate School, Department of Knowledge Technologies, Jamova 39, 1000 Ljubljana, Slovenia","institution_ids":["https://openalex.org/I4210113529"]},{"raw_affiliation_string":"Jo\u017eef Stefan Institute","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007096285","display_name":"Bla\u017e \u0160krlj","orcid":"https://orcid.org/0000-0002-9916-8756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bla\u017e \u0160krlj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074881863","display_name":"Senja Pollak","orcid":"https://orcid.org/0000-0002-4380-0863"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Senja Pollak","raw_affiliation_strings":["Joef Stefan Institute, Department of Knowledge Technologies, Jamova 39, 1000 Ljubljana, Slovenia and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joef Stefan Institute, Department of Knowledge Technologies, Jamova 39, 1000 Ljubljana, Slovenia and","institution_ids":["https://openalex.org/I3006985408"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8395,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77599391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"28","issue":"4","first_page":"409","last_page":"448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/T13083","display_name":"Advanced Text Analysis Techniques","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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.965499997138977,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9437000155448914,"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":0.8468655347824097},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7802566289901733},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7118676900863647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.62827467918396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5393981337547302},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5168821811676025},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5068050026893616},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46525388956069946},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4463441073894501},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39478984475135803},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09743478894233704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468655347824097},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7802566289901733},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7118676900863647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.62827467918396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5393981337547302},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5168821811676025},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5068050026893616},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46525388956069946},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4463441073894501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39478984475135803},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09743478894233704},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1017/s1351324921000127","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324921000127","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A41C8B12C1F3F4F02BF839FCAFA1A695/S1351324921000127a.pdf/div-class-title-tnt-kid-transformer-based-neural-tagger-for-keyword-identification-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:arXiv.org:2003.09166","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.09166","pdf_url":"https://arxiv.org/pdf/2003.09166","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:zenodo.org:5168413","is_oa":true,"landing_page_url":"https://zenodo.org/record/5168413","pdf_url":"https://zenodo.org/record/5168413","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Natural Language Engineering 1-40","raw_type":"info:eu-repo/semantics/article"},{"id":"mag:3012813596","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.09166.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.09166","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.09166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1017/s1351324921000127","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324921000127","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A41C8B12C1F3F4F02BF839FCAFA1A695/S1351324921000127a.pdf/div-class-title-tnt-kid-transformer-based-neural-tagger-for-keyword-identification-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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G5108423257","display_name":null,"funder_award_id":"825153","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5634946813","display_name":null,"funder_award_id":"2014-2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6870533126","display_name":null,"funder_award_id":"2014-2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7530123626","display_name":null,"funder_award_id":"P2-0103","funder_id":"https://openalex.org/F4320322554","funder_display_name":"Javna Agencija za Raziskovalno Dejavnost RS"},{"id":"https://openalex.org/G7641551787","display_name":null,"funder_award_id":"J6-9372","funder_id":"https://openalex.org/F4320322554","funder_display_name":"Javna Agencija za Raziskovalno Dejavnost RS"},{"id":"https://openalex.org/G8571498424","display_name":null,"funder_award_id":"J6-2581","funder_id":"https://openalex.org/F4320322554","funder_display_name":"Javna Agencija za Raziskovalno Dejavnost RS"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322554","display_name":"Javna Agencija za Raziskovalno Dejavnost RS","ror":"https://ror.org/059bp8k51"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3012813596.pdf","grobid_xml":"https://content.openalex.org/works/W3012813596.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W32253530","https://openalex.org/W95207536","https://openalex.org/W1490343430","https://openalex.org/W1528825546","https://openalex.org/W1565746575","https://openalex.org/W1604738109","https://openalex.org/W2014478203","https://openalex.org/W2030903088","https://openalex.org/W2045181608","https://openalex.org/W2060772621","https://openalex.org/W2062233052","https://openalex.org/W2064418625","https://openalex.org/W2071940869","https://openalex.org/W2102733276","https://openalex.org/W2129557600","https://openalex.org/W2133286915","https://openalex.org/W2142384583","https://openalex.org/W2143017621","https://openalex.org/W2145049651","https://openalex.org/W2147880316","https://openalex.org/W2167055467","https://openalex.org/W2167329753","https://openalex.org/W2250539671","https://openalex.org/W2250837944","https://openalex.org/W2250954789","https://openalex.org/W2251295945","https://openalex.org/W2295979112","https://openalex.org/W2400193661","https://openalex.org/W2493916176","https://openalex.org/W2546748700","https://openalex.org/W2604912255","https://openalex.org/W2605035112","https://openalex.org/W2740811004","https://openalex.org/W2789995212","https://openalex.org/W2790109590","https://openalex.org/W2804950764","https://openalex.org/W2842548026","https://openalex.org/W2888766462","https://openalex.org/W2890179025","https://openalex.org/W2894175714","https://openalex.org/W2896457183","https://openalex.org/W2907934657","https://openalex.org/W2935177567","https://openalex.org/W2938830017","https://openalex.org/W2943765965","https://openalex.org/W2948947170","https://openalex.org/W2949647400","https://openalex.org/W2953356739","https://openalex.org/W2957482284","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963250244","https://openalex.org/W2963265326","https://openalex.org/W2963275829","https://openalex.org/W2963341956","https://openalex.org/W2963345057","https://openalex.org/W2963631907","https://openalex.org/W2963670884","https://openalex.org/W2964110616","https://openalex.org/W2964165364","https://openalex.org/W2965373594","https://openalex.org/W2970771982","https://openalex.org/W2971674120","https://openalex.org/W2973226110","https://openalex.org/W2979553568","https://openalex.org/W2980598790","https://openalex.org/W2983288321","https://openalex.org/W2985875790","https://openalex.org/W2996726036","https://openalex.org/W3015316465","https://openalex.org/W3034379969","https://openalex.org/W3046517428","https://openalex.org/W4241727697","https://openalex.org/W4245267204","https://openalex.org/W6631501603","https://openalex.org/W6631793906","https://openalex.org/W6726378182","https://openalex.org/W6739901393","https://openalex.org/W6762088049","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W3170356364","https://openalex.org/W2951200021","https://openalex.org/W2097726176","https://openalex.org/W2951963554","https://openalex.org/W2250553586","https://openalex.org/W3037469642","https://openalex.org/W3023360076","https://openalex.org/W2914276272","https://openalex.org/W2945479064","https://openalex.org/W2250174247","https://openalex.org/W2137348499","https://openalex.org/W3024686163","https://openalex.org/W2899846447","https://openalex.org/W2017279302","https://openalex.org/W2980023977","https://openalex.org/W1989280373","https://openalex.org/W2152346074","https://openalex.org/W1981726983","https://openalex.org/W2734693922","https://openalex.org/W2181599973"],"abstract_inverted_index":{"Abstract":[0],"With":[1],"growing":[2],"amounts":[3],"of":[4,9,12,18,40,48,84,87,106,114,137,147,150],"available":[5],"textual":[6],"data,":[7],"development":[8],"algorithms":[10],"capable":[11,83],"automatic":[13],"analysis,":[14],"categorization,":[15],"and":[16,71,90,100,140],"summarization":[17],"these":[19],"data":[20,117],"has":[21],"become":[22],"a":[23,30,49,66,77,104,112],"necessity.":[24],"In":[25],"this":[26],"research,":[27],"we":[28],"present":[29],"novel":[31],"algorithm":[32],"for":[33,56,65],"keyword":[34,95,152],"identification,":[35],"that":[36],"is,":[37],"an":[38,141],"extraction":[39,96],"one":[41],"or":[42],"multiword":[43],"phrases":[44],"representing":[45],"key":[46],"aspects":[47],"given":[50],"document,":[51],"called":[52],"Transformer-Based":[53],"Neural":[54],"Tagger":[55],"Keyword":[57],"IDentification":[58],"(TNT-KID).":[59],"By":[60],"adapting":[61],"the":[62,80,120,134,138,145,151,156],"transformer":[63],"architecture":[64],"specific":[67,148],"task":[68],"at":[69],"hand":[70],"leveraging":[72],"language":[73],"model":[74,81,139],"pretraining":[75],"on":[76,103,155],"domain-specific":[78],"corpus,":[79],"is":[82],"overcoming":[85],"deficiencies":[86],"both":[88],"supervised":[89],"unsupervised":[91],"state-of-the-art":[92],"approaches":[93],"to":[94],"by":[97,119],"offering":[98],"competitive":[99],"robust":[101],"performance":[102],"variety":[105],"different":[107],"datasets":[108],"while":[109],"requiring":[110],"only":[111],"fraction":[113],"manually":[115],"labeled":[116],"required":[118],"best-performing":[121],"systems.":[122],"This":[123],"study":[124,143],"also":[125],"offers":[126],"thorough":[127],"error":[128],"analysis":[129],"with":[130],"valuable":[131],"insights":[132],"into":[133],"inner":[135],"workings":[136],"ablation":[142],"measuring":[144],"influence":[146],"components":[149],"identification":[153],"workflow":[154],"overall":[157],"performance.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}