Suivre
Belen Alastruey
Belen Alastruey
Meta AI
Adresse e-mail validée de meta.com
Titre
Citée par
Citée par
Année
Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer
J Ferrando, GI Gállego, B Alastruey, C Escolano, MR Costa-jussà
Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022
462022
On the Locality of Attention in Direct Speech Translation
B Alastruey, J Ferrando, GI Gállego, MR Costa-jussà
Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022
92022
The Gender-GAP Pipeline: A Gender-Aware Polyglot Pipeline for Gender Characterisation in 55 Languages
B Muller, B Alastruey, P Hansanti, E Kalbassi, C Ropers, EM Smith, ...
arXiv preprint arXiv:2308.16871, 2023
42023
Efficient Transformer for Direct Speech Translation
B Alastruey, GI Gállego, MR Costa-jussà
arXiv preprint arXiv:2107.03069, 2021
42021
Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation
G Sant, GI Gállego, B Alastruey, MR Costa-Jussà
Proceedings of the 2022 Conference of the North American Chapter of the …, 2022
32022
Large Concept Models: Language Modeling in a Sentence Representation Space
LCM The, L Barrault, PA Duquenne, M Elbayad, A Kozhevnikov, ...
arXiv preprint arXiv:2412.08821, 2024
2*2024
Towards Real-World Streaming Speech Translation for Code-Switched Speech
B Alastruey, M Sperber, C Gollan, DC Telaar, T Ng, A Agarwal
Sixth Workshop on Computational Approaches to Linguistic Code-Switching, 2023
22023
Linguini: A benchmark for language-agnostic linguistic reasoning
E Sánchez, B Alastruey, C Ropers, P Stenetorp, M Artetxe, ...
arXiv preprint arXiv:2409.12126, 2024
12024
SpeechAlign: a Framework for Speech Translation Alignment Evaluation
B Alastruey, A Sant, GI Gállego, D Dale, MR Costa-jussà
arXiv preprint arXiv:2309.11585, 2023
12023
2M-BELEBELE: Highly Multilingual Speech and American Sign Language Comprehension Dataset
MR Costa-jussà, B Yu, P Andrews, B Alastruey, NC Camgoz, J Chuang, ...
arXiv preprint arXiv:2412.08274, 2024
2024
Unveiling the Role of Pretraining in Direct Speech Translation
B Alastruey, GI Gállego, MR Costa-jussà
arXiv preprint arXiv:2409.18044, 2024
2024
Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition
B Alastruey, L Drude, J Heymann, S Wiesler
arXiv preprint arXiv:2306.06954, 2023
2023
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–12