6 papers
On the performance of phonetic algorithms in microtext normalization
Yerai Doval, Manuel Vilares, Jesús Vilares
User-generated content published on microblogging social networks constitutes a priceless source of information. However, microtexts usually deviate from the standard lexical and g…
Absolute convergence and error thresholds in non-active adaptive sampling
Manuel Vilares Ferro, Victor M. Darriba Bilbao, Jesús Vilares Ferro
Non-active adaptive sampling is a way of building machine learning models from a training data base which are supposed to dynamically and automatically derive guaranteed sample siz…
Adaptive scheduling for adaptive sampling in POS taggers construction
Manuel Vilares Ferro, Victor M. Darriba Bilbao, Jesús Vilares Ferro
We introduce an adaptive scheduling for adaptive sampling as a novel way of machine learning in the construction of part-of-speech taggers. The goal is to speed up the training on…
Modeling of learning curves with applications to pos tagging
Manuel Vilares Ferro, Victor M. Darriba Bilbao, Francisco J. Ribadas Pena
An algorithm to estimate the evolution of learning curves on the whole of a training data base, based on the results obtained from a portion and using a functional strategy, is int…
Early stopping by correlating online indicators in neural networks
Manuel Vilares Ferro, Yerai Doval Mosquera, Francisco J. Ribadas Pena +1
In order to minimize the generalization error in neural networks, a novel technique to identify overfitting phenomena when training the learner is formally introduced. This enables…
Surfing the modeling of PoS taggers in low-resource scenarios
Manuel Vilares Ferro, VÃctor M. Darriba Bilbao, Francisco J. Ribadas-Pena +1
The recent trend towards the application of deep structured techniques has revealed the limits of huge models in natural language processing. This has reawakened the interest in tr…