We propose a methodology for a novel type of discourse annotation whose model is tuned to the analysis of a text as narrative. This is intended to be the basis of a "story ba...
This paper presents a novel sequence labeling model based on the latent-variable semiMarkov conditional random fields for jointly extracting argument roles of events from texts. ...
This paper describes a new flexible representation for the annotation of complex structures of metadata over heterogeneous data collections containing text and other types of medi...
Our research aims at defining models and software tools in order to provide learners with a training memory. This memory is a computer-based space where a learner can organize and...
Motivation: Non-coding RNAs (ncRNAs)--functional RNA molecules not coding for proteins--are grouped into hundreds of families of homologs. To find new members of an ncRNA gene fam...