This paper deals with lexical acquisition. We take another look at some experiments we have recently carried out on the automatic acquisition of lexical resources from French corpora. We describe the architecture of our system for lexical acquisition. We formulate the hypothesis that some of the limitations of the current system are mainly due to a poor representation of the constraints used. Finally, we show how a better representation of constraints would yield better results.
© 2001-2025 Fundación Dialnet · Todos los derechos reservados