{"id":"https://openalex.org/W7204978345","doi":null,"title":"SMTE at ATE-IT: Ensemble Term Extraction with Italian BERT, spaCy, and Vocabulary-Based Filtering","display_name":"SMTE at ATE-IT: Ensemble Term Extraction with Italian BERT, spaCy, and Vocabulary-Based Filtering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204978345"},"language":"en","primary_location":{"id":"pmh:oai:www.research.unipd.it:11577/3609609","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11577/3609609","pdf_url":"https://ceur-ws.org/Vol-4195/10.pdf","source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ceur-ws.org/Vol-4195/10.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121853622","display_name":"Maule S.","orcid":null,"observed_orcids":[]},"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":"Maule S.","raw_affiliation_strings":["Department of Information Engineering , University of Padova , Via Gradenigo 6/b , 35131 Padova , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering , University of Padova , Via Gradenigo 6/b , 35131 Padova , Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134462447","display_name":"Di Nunzio G. M.","orcid":null,"observed_orcids":[]},"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":"Di Nunzio G. M.","raw_affiliation_strings":["Department of Information Engineering , University of Padova , Via Gradenigo 6/b , 35131 Padova , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering , University of Padova , Via Gradenigo 6/b , 35131 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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73372877,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9038000106811523,"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":0.9038000106811523,"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":0.08139999955892563,"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/T12881","display_name":"linguistics and terminology studies","score":0.006300000008195639,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/term-extraction","display_name":"term extraction","score":0.925000011920929},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.5419999957084656},{"id":"https://openalex.org/keywords/municipal-waste-management","display_name":"municipal solid waste management","score":0.7789999842643738},{"id":"https://openalex.org/keywords/institutional-texts","display_name":"institutional texts","score":0.8690000176429749},{"id":"https://openalex.org/keywords/term-normalization","display_name":"term normalization","score":0.5569999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730400025844574},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6966999769210815},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6035000085830688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5848000049591064},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5289000272750854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40849998593330383},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35269999504089355},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C3020613246","wikidata":"https://www.wikidata.org/wiki/Q1161829","display_name":"Third stage","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C134765980","wikidata":"https://www.wikidata.org/wiki/Q879126","display_name":"Bitwise operation","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C3020136221","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time sequence","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:www.research.unipd.it:11577/3609609","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11577/3609609","pdf_url":"https://ceur-ws.org/Vol-4195/10.pdf","source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"pmh:oai:www.research.unipd.it:11577/3609609","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11577/3609609","pdf_url":"https://ceur-ws.org/Vol-4195/10.pdf","source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204978345.pdf","grobid_xml":"https://content.openalex.org/works/W7204978345.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204979582","https://openalex.org/W7204979696","https://openalex.org/W7204973742","https://openalex.org/W7204983494","https://openalex.org/W7204974641","https://openalex.org/W7163216379","https://openalex.org/W3176491997","https://openalex.org/W3088593447","https://openalex.org/W3024396974","https://openalex.org/W3214399514"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,8,25,32,53,120],"SMTE":[4,58],"system":[5],"developed":[6],"for":[7,123,140],"shared":[9],"task":[10,45],"ATE-IT":[11],"(Subtask":[12],"A:":[13],"Automatic":[14],"Term":[15],"Extraction)":[16],"at":[17],"EVALITA":[18],"2026":[19],"in":[20,24],"Italian":[21,68],"institutional":[22],"texts":[23],"municipal":[26],"waste-management":[27],"domain.":[28],"Given":[29],"a":[30,66,81,92],"sentence,":[31],"goal":[33],"is":[34],"to":[35,76,86,99],"extract":[36],"domain-specific":[37],"single-":[38],"and":[39,52,90,102,109,115,118,125,133,138],"multi-word":[40],"terms":[41,98],"while":[42],"complying":[43],"with":[44,73],"constraints":[46],"such":[47],"as":[48],"lowercasing,":[49],"sentence-level":[50],"de-duplication,":[51],"removal":[54],"of":[55],"nested":[56,116],"terms.":[57],"follows":[59],"an":[60],"ensemble":[61],"approach":[62],"that":[63],"combines":[64],"(i)":[65],"fine-tuned":[67],"BERT":[69],"token-classification":[70],"model":[71],"trained":[72,82],"BIO":[74],"tags":[75],"detect":[77],"term":[78],"spans,":[79],"(ii)":[80],"spaCy":[83],"sequence":[84],"labeller":[85],"provide":[87],"complementary":[88],"candidates,":[89],"(iii)":[91],"vocabulary":[93],"built":[94],"from":[95],"gold":[96],"training":[97],"support":[100],"normalization":[101],"filtering.":[103],"A":[104],"final":[105],"post-processing":[106],"stage":[107],"cleans":[108],"canonicalises":[110],"predictions,":[111],"removes":[112],"truncated":[113],"spans":[114],"terms,":[117],"formats":[119],"output":[121],"JSON":[122],"evaluation":[124,131],"submission.":[126],"We":[127],"report":[128],"our":[129],"official":[130],"results":[132],"discuss":[134],"strengths,":[135],"typical":[136],"errors,":[137],"directions":[139],"future":[141],"improvements.":[142]},"counts_by_year":[],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2026-09-02T00:00:00"}