6 citations · 10 across the 2 of their papers we have counts for
5 papers · 1 filter
Structured Time Series Prediction without Structural Prior
Darko Drakulic, Jean-Marc Andreoli
Time series prediction is a widespread and well studied problem with applications in many domains (medical, geoscience, network analysis, finance, econometry etc.). In the case of…
Distributional Reinforcement Learning for Energy-Based Sequential Models
Tetiana Parshakova, Jean-Marc Andreoli, Marc Dymetman
Global Autoregressive Models (GAMs) are a recent proposal [Parshakova et al., CoNLL 2019] for exploiting global properties of sequences for data-efficient learning of seq2seq model…
Global Autoregressive Models for Data-Efficient Sequence Learning
Tetiana Parshakova, Jean-Marc Andreoli, Marc Dymetman
Standard autoregressive seq2seq models are easily trained by max-likelihood, but tend to show poor results under small-data conditions. We introduce a class of seq2seq models, GAMs…
Convolution, attention and structure embedding
Jean-Marc Andreoli
Deep neural networks are composed of layers of parametrised linear operations intertwined with non linear activations. In basic models, such as the multi-layer perceptron, a linear…
A conjugate prior for the Dirichlet distribution
Jean-Marc Andreoli
This note investigates a conjugate class for the Dirichlet distribution class in the exponential family.