Language resource quality is crucial in NLP. Many of the resources used are derived from data created by human beings out of an NLP context, especially regarding MT and reference ...
Recognizing polarity requires a list of polar words and phrases. For the purpose of building such lexicon automatically, a lot of studies have investigated (semi-) unsupervised me...
We use a generative history-based model to predict the most likely derivation of a dependency parse. Our probabilistic model is based on Incremental Sigmoid Belief Networks, a rec...
One of the arguments for choosing description logics as the basis for the Web Ontology Language is the ability to support the development of complex ontologies through logical reas...
Reservoir Computing is a new paradigm for using Recurrent Neural Networks which shows promising results. However, as the recurrent part is created randomly, it typically needs to b...
Xavier Dutoit, Benjamin Schrauwen, Jan M. Van Camp...