{"id":"https://openalex.org/W6999610679","doi":null,"title":"On Cross-Language Entity Label Projection and Recognition","display_name":"On Cross-Language Entity Label Projection and Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6999610679"},"language":"en","primary_location":{"id":"pmh:oai:cris.unibo.it:11585/1010767","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/1010767","pdf_url":"https://ceur-ws.org/Vol-3878/46_main_long.pdf","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ceur-ws.org/Vol-3878/46_main_long.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093291792","display_name":"Paolo Gajo","orcid":"https://orcid.org/0009-0009-9372-3323","observed_orcids":["https://orcid.org/0009-0009-9372-3323"]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Gajo","raw_affiliation_strings":["Universit\u00e0 di Bologna , Corso della Repubblica , 136 , 47121 , Forl\u00ec , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Bologna , Corso della Repubblica , 136 , 47121 , Forl\u00ec , Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":null,"display_name":"Alberto Barro\u0301n-Ceden\u0303o","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alberto Barro\u0301n-Ceden\u0303o","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"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":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.003700000001117587,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":9.999999747378752e-05,"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/multilingual-named-entity-recognition","display_name":"multilingual named entity recognition","score":0.8999999761581421},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.5699999928474426},{"id":"https://openalex.org/keywords/word-alignment","display_name":"word alignment","score":0.9629999995231628},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.671999990940094},{"id":"https://openalex.org/keywords/bert-fine-tuning","display_name":"BERT fine-tuning","score":0.8740000128746033},{"id":"https://openalex.org/keywords/out-of-domain-generalization","display_name":"out-of-domain generalization","score":0.6420000195503235},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.6919999718666077}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8549000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185999989509583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6984000205993652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6205999851226807},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6190999746322632},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.550000011920929},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4207000136375427},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3971000015735626},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:cris.unibo.it:11585/1010767","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/1010767","pdf_url":"https://ceur-ws.org/Vol-3878/46_main_long.pdf","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:cris.unibo.it:11585/1010767","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/1010767","pdf_url":"https://ceur-ws.org/Vol-3878/46_main_long.pdf","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"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":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/W6999610679.pdf","grobid_xml":"https://content.openalex.org/works/W6999610679.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1623072288","https://openalex.org/W2885185669","https://openalex.org/W2897709118","https://openalex.org/W2903298154","https://openalex.org/W2960374072","https://openalex.org/W2970849641","https://openalex.org/W3030163527","https://openalex.org/W3103942011","https://openalex.org/W3109664766","https://openalex.org/W3116194881","https://openalex.org/W3121602505","https://openalex.org/W3155609600","https://openalex.org/W3211686893","https://openalex.org/W4224308101","https://openalex.org/W4313483544","https://openalex.org/W4322718191","https://openalex.org/W4378498632","https://openalex.org/W4385573614","https://openalex.org/W4391158946","https://openalex.org/W4411120260","https://openalex.org/W7133224126"],"related_works":["https://openalex.org/W7166314623","https://openalex.org/W2972788481","https://openalex.org/W4385573847","https://openalex.org/W4312877554","https://openalex.org/W3121602505","https://openalex.org/W4385574235","https://openalex.org/W2973071945","https://openalex.org/W4393156794","https://openalex.org/W4210533572","https://openalex.org/W4416035193"],"abstract_inverted_index":{"Most":[0],"work":[1],"on":[2,9,148],"named":[3],"entity":[4,61],"recognition":[5],"(NER)":[6],"focuses":[7],"solely":[8],"English.":[10,119],"Through":[11],"the":[12,67,71,76,115,123,127,140,143,159],"use":[13,122],"of":[14,49,70,79,88,142,152],"training":[15,160],"data":[16,41,106,124,178],"augmentation":[17],"via":[18,111],"machine":[19],"translation":[20],"(MT),":[21],"multilingual":[22,33,134,191],"NER":[23,40,135,146,177,184],"can":[24],"become":[25],"a":[26,98],"powerful":[27],"tool":[28],"for":[29],"information":[30],"extraction":[31],"in":[32],"contexts.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,121],"augment":[39],"from":[42,104,118],"culinary":[43],"recipe":[44],"ingredient":[45,153],"lists":[46],"by":[47,126,180],"means":[48],"MT":[50],"and":[51,73,81,94,107,133,145],"word":[52],"alignment":[53],"(WA),":[54],"following":[55],"two":[56,128],"approaches:":[57],"(i)":[58],"translating":[59,75],"each":[60],"separately,":[62],"while":[63],"taking":[64],"into":[65],"account":[66],"full":[68],"context":[69],"list":[72,78],"(ii)":[74],"whole":[77],"ingredients":[80],"then":[82],"aligning":[83],"entities":[84,116,167],"using":[85,97],"three":[86],"types":[87],"WA":[89,144],"models:":[90],"Giza++,":[91],"Fast":[92],"Align,":[93],"BERT,":[95],"fine-tuned":[96],"novel":[99],"entity-shuffling":[100],"approach.":[101],"We":[102,138],"depart":[103],"English":[105],"produce":[108],"Italian":[109],"versions":[110],"MT,":[112],"span-annotated":[113],"with":[114,190],"projected":[117],"Then,":[120],"produced":[125],"approaches":[129],"to":[130,158,169,186,196],"train":[131],"mono-":[132],"BERT":[136,171],"models.":[137,173],"test":[139],"performance":[141],"models":[147,182,185,192],"an":[149],"annotated":[150],"dataset":[151],"lists,":[154],"partially":[155],"out-of-domain":[156],"compared":[157],"data.":[161],"The":[162,174],"results":[163],"show":[164],"that":[165],"shuffling":[166],"leads":[168],"better":[170,188],"aligner":[172],"higher":[175],"quality":[176],"created":[179],"these":[181],"enables":[183],"achieve":[187],"results,":[189],"reaching":[193],"performances":[194],"equal":[195],"or":[197],"greater":[198],"than":[199],"their":[200],"monolingual":[201],"counterparts.":[202]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}