40 citations
- Laboratoire Traitement et Communication de l’InformationFR14 papers
- KU LeuvenBE13 papers
- Institut Polytechnique de ParisFR7 papers
- Laboratoire Traitement du Signal et de l'ImageFR4 papers
- Télécom ParisFR4 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- Laboratoire d’Informatique et SystèmesFR3 papers
- Centre BorelliFR2 papers
- IBM (France)FR2 papers
- Institut national de recherche en sciences et technologies du numériqueFR2 papers
- Kyoto UniversityJP2 papers
- Laboratoire des signaux et systèmesFR2 papers
9 papers · 1 filter
Axiomatic characterization of the dissimilarity measure
Denis Bouyssou, Thierry Marchant, Marc Pirlot
We axiomatically characterize the dissimilarity measure. To this end, we solve a new generalization of a functional equation discussed in Aczel (Lectures on functional equa…
Code-switched inspired losses for generic spoken dialog representations
Emile Chapuis, Pierre Colombo, Matthieu Labeau +1
Spoken dialog systems need to be able to handle both multiple languages and multilinguality inside a conversation (\textit{e.g} in case of code-switching). In this work, we introdu…
Automatic Text Evaluation through the Lens of Wasserstein Barycenters
Pierre Colombo, Guillaume Staerman, Chloe Clavel +1
A new metric \texttt{BaryScore} to evaluate text generation based on deep contextualized embeddings e.g., BERT, Roberta, ELMo) is introduced. This metric is motivated by a new fram…
Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections
Kimia Nadjahi, Alain Durmus, Pierre E. Jacob +2
The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant computational…
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations
Pierre Colombo, Chloe Clavel, Pablo Piantanida
Learning disentangled representations of textual data is essential for many natural language tasks such as fair classification, style transfer and sentence generation, among others…
Concentration Inequalities for Two-Sample Rank Processes with Application to Bipartite Ranking
Stéphan Clémençon, Myrto Limnios, Nicolas Vayatis
The ROC curve is the gold standard for measuring the performance of a test/scoring statistic regarding its capacity to discriminate between two statistical populations in a wide va…