{"id":"https://openalex.org/W7166827226","doi":"https://doi.org/10.18653/v1/2026.bea-1.82","title":"Data Asgardians at BEA 2026 Shared Task 1: A Hybrid Transformer\u2013Feature Ensemble for L1-Aware English Vocabulary Difficulty Prediction","display_name":"Data Asgardians at BEA 2026 Shared Task 1: A Hybrid Transformer\u2013Feature Ensemble for L1-Aware English Vocabulary Difficulty Prediction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166827226","doi":"https://doi.org/10.18653/v1/2026.bea-1.82"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.bea-1.82","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.bea-1.82","pdf_url":"https://aclanthology.org/2026.bea-1.82.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":"Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.bea-1.82.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018316003","display_name":"Adrian Pineda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrian Pineda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122776960","display_name":"Sabur Butt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabur Butt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057149351","display_name":"H\u00e9ctor Ceballos Cancino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00e9ctor Ceballos Cancino","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.81692201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1137","last_page":"1145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.43869999051094055,"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":0.43869999051094055,"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/T13629","display_name":"Text Readability and Simplification","score":0.195700004696846,"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":0.10289999842643738,"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/task","display_name":"Task (project management)","score":0.6516000032424927},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5612000226974487},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.2815999984741211},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.2727000117301941},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.25519999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251999974250793},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6516000032424927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6079999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.583299994468689},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5612000226974487},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3513000011444092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.bea-1.82","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.bea-1.82","pdf_url":"https://aclanthology.org/2026.bea-1.82.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":"Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.bea-1.82","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.bea-1.82","pdf_url":"https://aclanthology.org/2026.bea-1.82.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":"Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6231147646903992}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166827226.pdf","grobid_xml":"https://content.openalex.org/works/W7166827226.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3,158],"system":[4],"for":[5,15,30,100],"the":[6,97],"BEA":[7],"2026":[8],"Shared":[9],"Task":[10],"on":[11],"Vocabulary":[12],"Difficulty":[13],"Prediction":[14],"English":[16,31],"Learners":[17],"(Felice":[18],"and":[19,44,66,69,79,91,113,129,144],"Skidmore,":[20],"2026).The":[21],"task":[22],"requires":[23],"predicting":[24],"psychometrically":[25],"calibrated":[26],"GLMM":[27],"difficulty":[28],"scores":[29],"vocabulary":[32],"items":[33],"across":[34],"three":[35,102],"learner":[36],"first-language":[37],"(L1)":[38],"backgrounds:":[39],"Spanish":[40],"(ES),":[41,110,141],"German":[42],"(DE),":[43,112,143],"Mandarin":[45],"Chinese":[46],"(CN).Our":[47],"approach":[48],"studies":[49],"how":[50],"hand-crafted":[51],"linguistic":[52],"features":[53],"can":[54],"complement":[55],"contextual":[56],"multilingual":[57],"transformer":[58,74,77],"representations.We":[59],"engineer":[60],"33":[61],"phonological,":[62],"morphological,":[63],"semantic,":[64],"contextual,":[65],"cross-lingual":[67],"features,":[68],"evaluate":[70],"feature-only":[71],"regressors,":[72],"Solo":[73,90],"models,":[75,78,93],"Hybrid":[76,92],"prediction-level":[80],"ensembling.Our":[81],"official":[82,98],"Closed":[83],"Track":[84],"submissions":[85],"were":[86],"generated":[87],"with":[88,116,147],"XLM-RoBERTa-large":[89,160],"which":[94,134],"improved":[95],"over":[96,157],"baseline":[99],"all":[101],"L1":[103],"groups,":[104],"achieving":[105],"test":[106,137],"RMSEs":[107],"of":[108,119,150,155],"1.182":[109],"1.117":[111],"1.006":[114],"(CN)":[115],"a":[117,123,130,148,152],"mean":[118,149,153],"1.103.We":[120],"then":[121],"conducted":[122],"post-submission":[124],"refinement":[125],"using":[126],"mDeBERTa-v3-base":[127],"components":[128],"Ridge":[131],"stacking":[132],"ensemble,":[133],"further":[135],"reduced":[136],"RMSE":[138],"to":[139],"1.037":[140],"0.997":[142],"0.913":[145],"(CN),":[146],"0.982,":[151],"improvement":[154],"0.121":[156],"best":[159],"system.":[161]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}