For years, recursive neural networks (RvNNs) have been shown to be suitable for representing text into fixed-length vectors and achieved good performance on several natural language processing tasks. However, the main drawback of RvNNs is that they require structured input, which makes data preparation and model implementation hard. In this paper, we propose Gumbel Tree-LSTM, a novel treestruct...

The results of an investigation on historical floods in four watersheds of the Aude region in France are presented herein. Using both, archive documents and field investigations, the discharges of the main historical floods could be estimated for a period ranging from one to two centuries. The use of this data, in addition to systematic discharge measurements (continuous series of about 30 year...

A new state space approach is proposed to model the time-dependence in an extreme value process. The generalized extreme value distribution is extended to incorporate the time-dependence using a state space representation where the state variables either follow an autoregressive (AR) process or a moving average (MA) process with innovations arising from a Gumbel distribution. Using a Bayesian a...

In this paper, the higher-order asymptotic expansion of the moment of extreme from generalized Maxwell distribution is gained, by which one establishes the rate of convergence of the moment of the normalized partial maximum to the moment of the associate Gumbel extreme value distribution.