• Batch-level GANs to promote dialogue response variety 

  López Zorrilla, Asier ; Vázquez Risco, Alain; Torres Barañano, María Inés (2023-02-24)

  Exploiting large pretrained transformers has become one of the most popular approaches for dialogue modelling. Nonetheless, due to their lack of robustness and explainability, we believe it is necessary to keep exploring ...
• Knowledge-grounded dialogue act transfer using prompt-based learning for controllable open-domain NLG 

  Vázquez Risco, Alain; Ramírez, Angela María; Pullabhotla, Neha; Qiang, Nan; Zhang, Haoran; Walker, Marilyn; Torres Barañano, María Inés (Association for Computational Linguistics, 2024-09)

  Open domain spoken dialogue systems need to controllably generate many different dialogue acts (DAs) to allow Natural Language Generation (NLG) to create interesting and engaging conversational interactions with users. We ...
• Reliable Explainability of Deep Learning Spatial-Spectral Classifiers for Improved Semantic Segmentation in Autonomous Driving 

  Gutiérrez Zaballa, Jon; Basterrechea Oyarzabal, Koldobika; Echanove Arias, Francisco Javier (IEEE, 2025-02-19)

  Integrating hyperspectral imagery (HSI) with deep neural networks (DNNs) can strengthen the accuracy of intelligent vision systems by combining spectral and spatial information, which is useful for tasks like semantic ...
• Designing DNNs for a trade-off between robustness and processing performance in embedded devices 

  Gutiérrez Zaballa, Jon; Basterrechea Oyarzabal, Koldobika; Echanove Arias, Francisco Javier (IEEE, 2024-12-03)

  Machine learning-based embedded systems employed in safety-critical applications such as aerospace and autonomous driving need to be robust against perturbations produced by soft errors. Soft errors are an increasing concern ...

View more