Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186241454> ?p ?o ?g. }
- W3186241454 abstract "Multilingual language models have been a crucial breakthrough as they considerably reduce the need of data for under-resourced languages. Nevertheless, the superiority of language-specific models has already been proven for languages having access to large amounts of data. In this work, we focus on Catalan with the aim to explore to what extent a medium-sized monolingual language model is competitive with state-of-the-art large multilingual models. For this, we: (1) build a clean, high-quality textual Catalan corpus (CaText), the largest to date (but only a fraction of the usual size of the previous work in monolingual language models), (2) train a Transformer-based language model for Catalan (BERTa), and (3) devise a thorough evaluation in a diversity of settings, comprising a complete array of downstream tasks, namely, Part of Speech Tagging, Named Entity Recognition and Classification, Text Classification, Question Answering, and Semantic Textual Similarity, with most of the corresponding datasets being created ex novo. The result is a new benchmark, the Catalan Language Understanding Benchmark (CLUB), which we publish as an open resource, together with the clean textual corpus, the language model, and the cleaning pipeline. Using state-of-the-art multilingual models and a monolingual model trained only on Wikipedia as baselines, we consistently observe the superiority of our model across tasks and settings." @default.
- W3186241454 created "2021-08-02" @default.
- W3186241454 creator A5020795476 @default.
- W3186241454 creator A5044768193 @default.
- W3186241454 creator A5045074263 @default.
- W3186241454 creator A5046596536 @default.
- W3186241454 creator A5049663811 @default.
- W3186241454 creator A5050567810 @default.
- W3186241454 creator A5080671910 @default.
- W3186241454 creator A5080796123 @default.
- W3186241454 date "2021-07-16" @default.
- W3186241454 modified "2023-09-27" @default.
- W3186241454 title "Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan" @default.
- W3186241454 cites W2131744502 @default.
- W3186241454 cites W2251861449 @default.
- W3186241454 cites W2252198292 @default.
- W3186241454 cites W2493916176 @default.
- W3186241454 cites W2798712760 @default.
- W3186241454 cites W2911227954 @default.
- W3186241454 cites W2933138175 @default.
- W3186241454 cites W2948902769 @default.
- W3186241454 cites W2963310665 @default.
- W3186241454 cites W2963341956 @default.
- W3186241454 cites W2963403868 @default.
- W3186241454 cites W2963748441 @default.
- W3186241454 cites W2965373594 @default.
- W3186241454 cites W2978017171 @default.
- W3186241454 cites W2995647371 @default.
- W3186241454 cites W2996580882 @default.
- W3186241454 cites W3009095382 @default.
- W3186241454 cites W3030394039 @default.
- W3186241454 cites W3033940819 @default.
- W3186241454 cites W3034469191 @default.
- W3186241454 cites W3035032094 @default.
- W3186241454 cites W3035390927 @default.
- W3186241454 cites W3035497479 @default.
- W3186241454 cites W3098903812 @default.
- W3186241454 cites W3099756172 @default.
- W3186241454 cites W3109959371 @default.
- W3186241454 cites W630532510 @default.
- W3186241454 hasPublicationYear "2021" @default.
- W3186241454 type Work @default.
- W3186241454 sameAs 3186241454 @default.
- W3186241454 citedByCount "0" @default.
- W3186241454 crossrefType "posted-content" @default.
- W3186241454 hasAuthorship W3186241454A5020795476 @default.
- W3186241454 hasAuthorship W3186241454A5044768193 @default.
- W3186241454 hasAuthorship W3186241454A5045074263 @default.
- W3186241454 hasAuthorship W3186241454A5046596536 @default.
- W3186241454 hasAuthorship W3186241454A5049663811 @default.
- W3186241454 hasAuthorship W3186241454A5050567810 @default.
- W3186241454 hasAuthorship W3186241454A5080671910 @default.
- W3186241454 hasAuthorship W3186241454A5080796123 @default.
- W3186241454 hasConcept C120665830 @default.
- W3186241454 hasConcept C121332964 @default.
- W3186241454 hasConcept C13280743 @default.
- W3186241454 hasConcept C137293760 @default.
- W3186241454 hasConcept C138885662 @default.
- W3186241454 hasConcept C154945302 @default.
- W3186241454 hasConcept C164105321 @default.
- W3186241454 hasConcept C185798385 @default.
- W3186241454 hasConcept C192209626 @default.
- W3186241454 hasConcept C204321447 @default.
- W3186241454 hasConcept C205649164 @default.
- W3186241454 hasConcept C2780035574 @default.
- W3186241454 hasConcept C41008148 @default.
- W3186241454 hasConcept C41895202 @default.
- W3186241454 hasConceptScore W3186241454C120665830 @default.
- W3186241454 hasConceptScore W3186241454C121332964 @default.
- W3186241454 hasConceptScore W3186241454C13280743 @default.
- W3186241454 hasConceptScore W3186241454C137293760 @default.
- W3186241454 hasConceptScore W3186241454C138885662 @default.
- W3186241454 hasConceptScore W3186241454C154945302 @default.
- W3186241454 hasConceptScore W3186241454C164105321 @default.
- W3186241454 hasConceptScore W3186241454C185798385 @default.
- W3186241454 hasConceptScore W3186241454C192209626 @default.
- W3186241454 hasConceptScore W3186241454C204321447 @default.
- W3186241454 hasConceptScore W3186241454C205649164 @default.
- W3186241454 hasConceptScore W3186241454C2780035574 @default.
- W3186241454 hasConceptScore W3186241454C41008148 @default.
- W3186241454 hasConceptScore W3186241454C41895202 @default.
- W3186241454 hasLocation W31862414541 @default.
- W3186241454 hasOpenAccess W3186241454 @default.
- W3186241454 hasPrimaryLocation W31862414541 @default.
- W3186241454 hasRelatedWork W2022752172 @default.
- W3186241454 hasRelatedWork W2892107559 @default.
- W3186241454 hasRelatedWork W2976042047 @default.
- W3186241454 hasRelatedWork W2983577274 @default.
- W3186241454 hasRelatedWork W2986154550 @default.
- W3186241454 hasRelatedWork W2995647371 @default.
- W3186241454 hasRelatedWork W2998272617 @default.
- W3186241454 hasRelatedWork W3012990076 @default.
- W3186241454 hasRelatedWork W3014346867 @default.
- W3186241454 hasRelatedWork W3030394039 @default.
- W3186241454 hasRelatedWork W3032433061 @default.
- W3186241454 hasRelatedWork W3094458375 @default.
- W3186241454 hasRelatedWork W3099919888 @default.
- W3186241454 hasRelatedWork W3118580427 @default.
- W3186241454 hasRelatedWork W3136221257 @default.
- W3186241454 hasRelatedWork W3175567752 @default.