Unsupervised features based on word representations such as word embeddings and word collocations have shown to significantly improve supervised NER for English. In this work we investigate whether such unsupervised features ...

In this paper we present an unsupervised segmentation-free method for spotting and searching query, especially, for images documents in handwritten Arabic, for this, Histograms of Oriented Gradients (HOGs) are used as the ...

This dissertation aims at investigating the variable segmental reduction in initial #(i)sC sequences in the Belo Horizonte variety of Brazilian Portuguese, in words such as escola [iskl] ~ [skl] ou skate [iske] ~ [ske]. ...

In order to learn an oral language, humans have to discover words from a continuous signal. Streams of artificial monotonous speech can be readily segmented based on the statistical analysis of the syllables' distribution. ...

Unsupervised features such as word representations mostly given by word embeddings have been shown significantly improve semi supervised Named Entity Recognition (NER) for English language. In this work we investigate ...

The aim of this research is to characterize the hypo-segmentations in nineteenth-century manuscripts of the Municipal Council from the Rio Pardo City, in the Rio Grande do Sul, under the theoretical contribution of the ...