{"id":"https://openalex.org/W4413796110","doi":"https://doi.org/10.3233/ssw250013","title":"DA-ATE: Data Augmentation for Automatic Term Extraction","display_name":"DA-ATE: Data Augmentation for Automatic Term Extraction","publication_year":2025,"publication_date":"2025-08-26","ids":{"openalex":"https://openalex.org/W4413796110","doi":"https://doi.org/10.3233/ssw250013"},"language":"en","primary_location":{"id":"doi:10.3233/ssw250013","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ssw250013","pdf_url":null,"source":{"id":"https://openalex.org/S4210172742","display_name":"Studies on the semantic web","issn_l":"2215-0870","issn":["2215-0870"],"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":"ebook platform"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies on the Semantic Web","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/ssw250013","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046099447","display_name":"Shubhanker Banerjee","orcid":"https://orcid.org/0000-0002-3969-5183"},"institutions":[{"id":"https://openalex.org/I168346926","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38","country_code":"IE","type":"nonprofit","lineage":["https://openalex.org/I168346926"]},{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Shubhanker Banerjee","raw_affiliation_strings":["Research Ireland ADAPT Centre, University of Galway, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-3969-5183","affiliations":[{"raw_affiliation_string":"Research Ireland ADAPT Centre, University of Galway, Ireland","institution_ids":["https://openalex.org/I188760350","https://openalex.org/I168346926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024482506","display_name":"Bharathi Raja Chakravarthi","orcid":"https://orcid.org/0000-0002-4575-7934"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Bharathi Raja Chakravarthi","raw_affiliation_strings":["Department of Computer Science, University of Galway, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-4575-7934","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036503167","display_name":"John P. McCrae","orcid":"https://orcid.org/0000-0002-7227-1331"},"institutions":[{"id":"https://openalex.org/I168346926","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38","country_code":"IE","type":"nonprofit","lineage":["https://openalex.org/I168346926"]},{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"John P. McCrae","raw_affiliation_strings":["Research Ireland ADAPT Centre, University of Galway, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-7227-1331","affiliations":[{"raw_affiliation_string":"Research Ireland ADAPT Centre, University of Galway, Ireland","institution_ids":["https://openalex.org/I188760350","https://openalex.org/I168346926"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046099447"],"corresponding_institution_ids":["https://openalex.org/I168346926","https://openalex.org/I188760350"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37154797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9997000098228455,"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":0.9997000098228455,"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/T13083","display_name":"Advanced Text Analysis Techniques","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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.790331244468689},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.6766304969787598},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6692472696304321},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5486956834793091},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.548343300819397},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.538930356502533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5154138803482056},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4123910367488861},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37751221656799316},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.368984192609787},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3502234220504761},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.058714091777801514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790331244468689},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.6766304969787598},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6692472696304321},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5486956834793091},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.548343300819397},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.538930356502533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5154138803482056},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4123910367488861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37751221656799316},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.368984192609787},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3502234220504761},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.058714091777801514},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/ssw250013","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ssw250013","pdf_url":null,"source":{"id":"https://openalex.org/S4210172742","display_name":"Studies on the semantic web","issn_l":"2215-0870","issn":["2215-0870"],"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":"ebook platform"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies on the Semantic Web","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/ssw250013","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ssw250013","pdf_url":null,"source":{"id":"https://openalex.org/S4210172742","display_name":"Studies on the semantic web","issn_l":"2215-0870","issn":["2215-0870"],"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":"ebook platform"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies on the Semantic Web","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2350593162","https://openalex.org/W2390350206","https://openalex.org/W1969477129","https://openalex.org/W2921208823","https://openalex.org/W2353483812","https://openalex.org/W2131808775","https://openalex.org/W2130038259","https://openalex.org/W2360756181","https://openalex.org/W2374093222","https://openalex.org/W2359533638"],"abstract_inverted_index":{"Automatic":[0],"term":[1],"extraction":[2],"(ATE)":[3],"identifies":[4],"domain-specific":[5],"concepts":[6],"from":[7,12],"specialized":[8],"corpora,":[9],"but":[10],"suffers":[11],"limited":[13],"annotated":[14],"training":[15,66],"data":[16,25,125,131],"across":[17,69,129],"diverse":[18,33],"domains.":[19],"We":[20],"propose":[21],"three":[22],"novel":[23,49],"LLM-based":[24],"augmentation":[26,31,39,47,106,126],"schemes":[27],"for":[28,127],"ATE:":[29],"context-level":[30],"(generating":[32],"sentences":[34,50],"using":[35],"existing":[36],"terms),":[37],"term-level":[38,105],"(replacing":[40],"terms":[41],"with":[42,51,83,134],"domain-relevant":[43],"alternatives),":[44],"and":[45,59,95,104],"combined":[46,109],"(creating":[48],"new":[52],"terminology).":[53],"Our":[54,118],"approach":[55],"leverages":[56],"both":[57],"ChatGPT-4o":[58],"Wikipedia-derived":[60],"domain":[61],"lexicons":[62],"to":[63,87,141],"generate":[64],"synthetic":[65],"data.":[67],"Experiments":[68],"four":[70],"domains":[71],"in":[72,90,98],"the":[73,121],"ACTER":[74],"dataset":[75,143],"demonstrate":[76],"consistent":[77],"improvements":[78,97],"over":[79],"state-of-the-art":[80],"XLM-RoBERTa":[81],"baselines,":[82],"gains":[84,136],"of":[85,123],"up":[86],"28%":[88],"F1-score":[89],"few-shot":[91,139],"scenarios":[92],"(5-10":[93],"samples)":[94],"1-2%":[96],"larger":[99],"datasets":[100],"(100-500":[101],"samples).":[102],"Context-level":[103],"consistently":[107],"outperform":[108],"augmentation,":[110],"while":[111],"LLM-":[112],"based":[113],"methods":[114],"surpass":[115],"Wikipedia-based":[116],"augmentation.":[117],"findings":[119],"establish":[120],"effectiveness":[122],"targeted":[124],"ATE":[128],"varying":[130],"availability":[132],"scenarios,":[133],"performance":[135],"extending":[137],"beyond":[138],"settings":[140],"practical":[142],"sizes.":[144]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}