(2022 - 2024)
DeepR3 will investigate new efficient methods to extend, reuse and adapt existing pre-trained language models for Spanish, Catalan, Basque, Galician plus English to be exploited in new domains, genres and languages for being applied to different use cases such as the biomedical domain, machine translation or text generation from meteorological data. The results of DeepR3 will have a direct impact on both the Ecological Transition by avoiding unnecessary waste of energy and the Digital Transition by creating better language models for more languages that can be applied to multiple NLP tasks.
Argitalpenetan honako hau jarri:
DeepR3 (TED2021-130295B-C31) founded by MCIN/AEI/10.13039/501100011033 and European Union NextGeneration EU/PRTR.
Organization: Ministerio de Ciencia e Innovación
Main researcher: Aitor Soroa, German Rigau
Nora Aranberri, Aitziber Atutxa, Josu Goikoetxea, Koldo Gojenola, Gorka Labaka, German Rigau , Aitor Soroa