In this paper, we present a new approximation in Natural Language Processing (nlp) aimed at knowledge representation and acquisition using a formal syntactic frame. In practice, we...
We introduce a semi-supervised approach to training for statistical machine translation that alternates the traditional Expectation Maximization step that is applied on a large tr...
Abstract The paper overviews the vandalism detection task of the PAN’11 competition. A new corpus is introduced which comprises about 30 000 Wikipedia edits in the languages Engl...
In the context of deployed spoken dialogue telecom services, we introduce a preprocessor called Fiction into the Spoken Language Understanding (SLU) component. It acts as an inter...
Abstract.Abstract.Abstract. This article outlines a three-party conversation corpus built by the National Institute of Information and Communications Technology (Section 2) and int...