10 papers
CAMMAR: Culture-Aware Matryoshka for Metaphorical Arabic Representations
Suzan Awinat, Alfonso Ortega del Puente
Metaphor in Arabic is a culturally grounded mechanism for constructing meaning, encoding cultural knowledge that shapes interpretation. Yet current Arabic language models typically…
Bridging Functional and Representational Similarity via Usable Information
Antonio Almudévar, Alfonso Ortega
We present a unified framework for quantifying the similarity between representations through the lens of \textit{usable} information, offering a rigorous theoretical and empirical…
Representation Unlearning: Forgetting through Information Compression
Antonio Almudévar, Alfonso Ortega
Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concerns. Existing approaches typically…
Aligning Multimodal Representations through an Information Bottleneck
Antonio Almudévar, José Miguel Hernández-Lobato, Sameer Khurana +2
Contrastive losses have been extensively used as a tool for multimodal representation learning. However, it has been empirically observed that their use is not effective to learn a…
There Was Never a Bottleneck in Concept Bottleneck Models
Antonio Almudévar, José Miguel Hernández-Lobato, Alfonso Ortega
Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs) have emerged as a prom…
Angular Distance Distribution Loss for Audio Classification
Antonio Almudévar, Romain Serizel, Alfonso Ortega
Classification is a pivotal task in deep learning not only because of its intrinsic importance, but also for providing embeddings with desirable properties in other tasks. To optim…
Predefined Prototypes for Intra-Class Separation and Disentanglement
Antonio Almudévar, Théo Mariotte, Alfonso Ortega +4
Prototypical Learning is based on the idea that there is a point (which we call prototype) around which the embeddings of a class are clustered. It has shown promising results in s…
Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing
Martin Lebourdais, Théo Mariotte, Antonio Almudévar +2
Audio segmentation is a key task for many speech technologies, most of which are based on neural networks, usually considered as black boxes, with high-level performances. However,…
Unsupervised Multiple Domain Translation through Controlled Disentanglement in Variational Autoencoder
Antonio Almudévar, Théo Mariotte, Alfonso Ortega +1
Unsupervised Multiple Domain Translation is the task of transforming data from one domain to other domains without having paired data to train the systems. Typically, methods based…
An Explainable Proxy Model for Multiabel Audio Segmentation
Théo Mariotte, Antonio Almudévar, Marie Tahon +1
Audio signal segmentation is a key task for automatic audio indexing. It consists of detecting the boundaries of class-homogeneous segments in the signal. In many applications, exp…