{"id":"https://openalex.org/W7140145250","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.135","title":"Binary Token-Level Classification with DeBERTa for All-Type MWE Identification: A Lightweight Approach with Linguistic Enhancement","display_name":"Binary Token-Level Classification with DeBERTa for All-Type MWE Identification: A Lightweight Approach with Linguistic Enhancement","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140145250","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.135"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.135","pdf_url":"https://aclanthology.org/2026.findings-eacl.135.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.135.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Diego Rossini","orcid":null},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Diego Rossini","raw_affiliation_strings":["Universit della Svizzera Italiana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit della Svizzera Italiana","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lonneke Van Der Plas","orcid":null},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lonneke Van Der Plas","raw_affiliation_strings":["Universit della Svizzera Italiana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit della Svizzera Italiana","institution_ids":["https://openalex.org/I57201433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57201433"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30673376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2600","last_page":"2610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12131","display_name":"Wireless Signal Modulation Classification","score":0.04619999974966049,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.04619999974966049,"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/T11021","display_name":"ECG Monitoring and Analysis","score":0.03550000116229057,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.025200000032782555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4043000042438507},{"id":"https://openalex.org/keywords/binary-data","display_name":"Binary data","score":0.31859999895095825},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.29339998960494995},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2784999907016754},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.27649998664855957},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2678999900817871}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5654000043869019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48989999294281006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4077000021934509},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C2779190172","wikidata":"https://www.wikidata.org/wiki/Q4913888","display_name":"Binary data","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.135","pdf_url":"https://aclanthology.org/2026.findings-eacl.135.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.135","pdf_url":"https://aclanthology.org/2026.findings-eacl.135.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5646008450","display_name":null,"funder_award_id":"51NF40_180888","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140145250.pdf","grobid_xml":"https://content.openalex.org/works/W7140145250.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"comprehensive":[3],"approach":[4],"for":[5,123],"multiword":[6],"expression":[7],"(MWE)":[8],"identification":[9],"that":[10,72,83,107],"combines":[11],"binary":[12,57],"token-level":[13,58],"classification,":[14],"linguistic":[15],"feature":[16],"integration,":[17],"and":[18,69,75,79],"data":[19],"augmentation.":[20],"1Our":[21],"DeBERTa-v3-large":[22],"model":[23],"achieves":[24],"69.8%":[25],"F1":[26],"on":[27,38,98,116],"the":[28,32,89,93,99],"CoAM":[29],"dataset,":[30,101],"surpassing":[31],"best":[33],"results":[34,105],"(Qwen-72B,":[35],"57.8%":[36],"F1)":[37],"this":[39,50],"dataset":[40],"by":[41,52],"12":[42],"points":[43],"while":[44],"using":[45],"165":[46],"fewer":[47],"parameters.We":[48],"achieve":[49],"performance":[51],"(1)":[53],"reformulating":[54],"detection":[55],"as":[56],"START/END/INSIDE":[59],"classification":[60],"rather":[61],"than":[62],"span-based":[63],"prediction,":[64],"(2)":[65],"incorporating":[66],"NP":[67],"chunking":[68],"dependency":[70],"features":[71],"help":[73],"discontinuous":[74],"NOUN-type":[76],"MWEs":[77],"identification,":[78],"(3)":[80],"applying":[81],"oversampling":[82],"addresses":[84],"severe":[85],"class":[86],"imbalance":[87],"in":[88],"training":[90],"data.We":[91],"confirm":[92],"generalization":[94],"of":[95],"our":[96],"method":[97],"STREUSLE":[100],"achieving":[102],"78.9%":[103],"F1.These":[104],"demonstrate":[106],"carefully":[108],"designed":[109],"smaller":[110],"models":[111],"can":[112],"substantially":[113],"outperform":[114],"LLMs":[115],"structured":[117],"NLP":[118],"tasks,":[119],"with":[120],"important":[121],"implications":[122],"resourceconstrained":[124],"deployments.":[125]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2026-02-02T00:00:00"}