{"id":"https://openalex.org/W4398186424","doi":"https://doi.org/10.1145/3605098.3636010","title":"Improving Soft Skill Extraction via Data Augmentation and Embedding Manipulation","display_name":"Improving Soft Skill Extraction via Data Augmentation and Embedding Manipulation","publication_year":2024,"publication_date":"2024-04-08","ids":{"openalex":"https://openalex.org/W4398186424","doi":"https://doi.org/10.1145/3605098.3636010"},"language":"en","primary_location":{"id":"doi:10.1145/3605098.3636010","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605098.3636010","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605098.3636010","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 39th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3605098.3636010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044325079","display_name":"Muhammad Uzair Ul Haq","orcid":"https://orcid.org/0000-0001-9660-8982"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Muhammad Uzair Ul Haq","raw_affiliation_strings":["University of Padova, Padova, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9660-8982","affiliations":[{"raw_affiliation_string":"University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091584093","display_name":"Paolo Frazzetto","orcid":"https://orcid.org/0000-0002-3227-0019"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Frazzetto","raw_affiliation_strings":["University of Padova, Padova, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3227-0019","affiliations":[{"raw_affiliation_string":"University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064873591","display_name":"Alessandro Sperduti","orcid":"https://orcid.org/0000-0002-8686-850X"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Sperduti","raw_affiliation_strings":["University of Padua, Padova, Italy"],"raw_orcid":"https://orcid.org/0000-0002-8686-850X","affiliations":[{"raw_affiliation_string":"University of Padua, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033850423","display_name":"Giovanni Da San Martino","orcid":"https://orcid.org/0000-0002-2609-483X"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Da San Martino","raw_affiliation_strings":["University of Padova, Padova, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2609-483X","affiliations":[{"raw_affiliation_string":"University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"987","last_page":"996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9789000153541565,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9789000153541565,"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/embedding","display_name":"Embedding","score":0.7119128704071045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.699116587638855},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.6010805368423462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41050103306770325},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3271523118019104}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7119128704071045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.699116587638855},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6010805368423462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41050103306770325},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3271523118019104},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3605098.3636010","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605098.3636010","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605098.3636010","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 39th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:www.research.unipd.it:11577/3527981","is_oa":true,"landing_page_url":"https://hdl.handle.net/11577/3527981","pdf_url":"https://www.research.unipd.it/bitstream/11577/3527981/1/3605098.3636010.pdf","source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3605098.3636010","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605098.3636010","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605098.3636010","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 39th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321966","display_name":"Universit\u00e0 degli Studi di Padova","ror":"https://ror.org/00240q980"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4398186424.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1554578572","https://openalex.org/W2053730693","https://openalex.org/W2099196804","https://openalex.org/W2299976354","https://openalex.org/W2760505947","https://openalex.org/W2946068894","https://openalex.org/W2963216553","https://openalex.org/W2963545917","https://openalex.org/W2971296908","https://openalex.org/W2997546679","https://openalex.org/W3097513514","https://openalex.org/W3104182623","https://openalex.org/W3115908473","https://openalex.org/W3122230467","https://openalex.org/W3134583732","https://openalex.org/W3196024535","https://openalex.org/W4200280488","https://openalex.org/W4252110927","https://openalex.org/W4285106586","https://openalex.org/W4292315287"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Soft":[0],"skills":[1,210],"(SS)":[2],"are":[3,84,157],"important":[4],"for":[5,13,61,152,208,245],"Human":[6],"Resource":[7],"Management":[8],"when":[9,129],"recruiting":[10],"suitable":[11],"candidates":[12],"a":[14,93,111],"job.":[15],"Nowadays,":[16],"enterprises":[17],"aim":[18],"to":[19,32,54,69,86,148,159,190,222,236],"automatically":[20],"extract":[21,87],"such":[22],"information":[23],"from":[24],"documents,":[25],"curriculum":[26],"vitae":[27],"(CVs)":[28],"and":[29,67,212,220],"job":[30],"descriptions,":[31],"speed":[33],"up":[34],"their":[35],"recruitment":[36],"process.":[37],"State-of-the-art":[38],"Large":[39],"Language":[40,48],"Models":[41],"(LLMs)":[42],"have":[43],"been":[44],"successful":[45],"in":[46,110,176],"Natural":[47],"Processing":[49],"(NLP)":[50],"by":[51,173],"fine-tuning":[52],"them":[53],"the":[55,62,95,98,130,143,164,170,178,193,203,224,231,242,246],"domain-specific":[56],"task.":[57],"However,":[58],"annotated":[59,90],"data":[60,119,151],"task":[63],"is":[64,133],"very":[65],"limited":[66],"costly":[68],"obtain,":[70],"since":[71],"it":[72],"requires":[73],"domain":[74],"experts.":[75],"Moreover,":[76,140],"SS":[77],"consists":[78],"of":[79,97,145,163,181,195],"complex":[80],"long":[81,134],"entities":[82],"which":[83,125],"difficult":[85],"given":[88],"few":[89],"examples.":[91],"As":[92],"consequence,":[94],"performance":[96,128,144,194],"LLMs":[99,147],"on":[100,202,213],"soft":[101,209,247],"skill":[102],"detection":[103],"still":[104],"needs":[105],"improvement":[106],"before":[107],"being":[108],"used":[109,158],"real-world":[112],"context.":[113],"In":[114],"this":[115],"paper,":[116],"we":[117,141],"introduce":[118],"augmentation":[120,162],"based":[121],"entity":[122,131],"extraction":[123,179],"approach":[124,189,201,233],"shows":[126,229],"promising":[127],"length":[132],"(i.e":[135],"more":[136],"than":[137],"three":[138,214],"tokens).":[139],"explore":[142],"pre-trained":[146,155],"generate":[149,160],"synthetic":[150],"training.":[153],"The":[154],"models":[156,175],"contextual":[161],"baseline":[165,196,243],"dataset.":[166],"We":[167,183,198],"further":[168,191],"analyse":[169],"embeddings":[171],"generated":[172],"these":[174],"aiding":[177],"process":[180],"entities.":[182],"develop":[184],"an":[185],"Embedding":[186],"Manipulation":[187],"(EM)":[188],"improve":[192],"models.":[197],"evaluated":[199],"our":[200],"only":[204],"publicly":[205],"available":[206],"dataset":[207],"(SKILLSPAN),":[211],"Entity":[215],"Extraction":[216],"datasets":[217],"(GUM,":[218],"WNUT-2017":[219],"CoNLL-2003)":[221],"assess":[223],"proposed":[225,232],"approach.":[226],"Empirical":[227],"evidence":[228],"that":[230],"allows":[234],"us":[235],"get":[237],"6.52%":[238],"increased":[239],"F1":[240],"over":[241],"model":[244],"skills.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}