The Conference on Computational Natural Language Learning features a shared task, in which participants train and test their learning systems on the same data sets. In 2007, as in...
We describe two probabilistic models for unsupervised word-sense disambiguation using parallel corpora. The first model, which we call the Sense model, builds on the work of Diab ...
Recent works about the activity-oriented approach et educational modeling languages ask questions about the pedagogical scenario concept. The aim of this paper is to define the fo...
This paper describes a model of the emergence and the universal structural tendencies of vowel systems. Both are considered as the result of self-organisation in a population of l...
We present a unified view of two state-of-theart non-projective dependency parsers, both approximate: the loopy belief propagation parser of Smith and Eisner (2008) and the relaxe...