CreoleVal: Multilingual Multitask Benchmarks for Creoles

Autor: Lent, Heather, Tatariya, Kushal, Dabre, Raj, Chen, Yiyi, Fekete, Marcell, Ploeger, Esther, Zhou, Li, Armstrong, Ruth-Ann, Eijansantos, Abee, Malau, Catriona, Heje, Hans Erik, Lavrinovics, Ernests, Kanojia, Diptesh, Belony, Paul, Bollmann, Marcel, Grobol, Loïc, de Lhoneux, Miryam, Hershcovich, Daniel, DeGraff, Michel, Søgaard, Anders, Bjerva, Johannes

Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research.While the genealogical ties between Creoles and a number of highly-resourced languages imply a significant potential for transfer l

Externí odkaz: http://arxiv.org/abs/2310.19567

Gradual Language Model Adaptation Using Fine-Grained Typology

Autor: Fekete, Marcell Richard, Bjerva, Johannes

Publikováno v: Fekete, M R & Bjerva, J 2023, Gradual Language Model Adaptation Using Fine-Grained Typology . in Proceedings of the Workshop on Computational Research in Linguistic Typology . Association for Computational Linguistics, The 17th Conference of the European Chapter of the Association for Computational Linguistics, Dubrovnik, Croatia, 02/05/2023 . < https://sigtyp.github.io/workshops/2023/sigtyp/papers/16_gradual_language_model_adaptat.pdf >

Transformer-based language models (LMs) offer superior performance in a wide range of NLP tasks compared to previous paradigms. However, the vast majority of the world's languages do not have adequate training data available for monolingual LMs (Josh

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::22795697c33c9d70ba5e97d98c2f885a
https://vbn.aau.dk/da/publications/b5f24683-93ff-4d9b-bab6-51074e3b056d