Pedro Miguel Dias Cardoso

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
In this paper we explain how we created a labelled corpus in English for a Named Entity Recognition (NER) task from multi-source and multi-domain data, for an industrial partner. We explain the specificities of this corpus with examples and describe some baseline experiments. We present some results of domain adaptation on this corpus using a labelled(More)
This work presents a novel approach for automatic creation of sentiment word lists. In this approach, words are first mapped into a continuous latent space, which serves as input to a multilayer perceptron (MLP) trained using sentiment-annotated words. When evaluated using manually annotated EmoLex corpus, our approach compares favourably with SentiWordNet(More)
  • 1