Bayesian Network, a model for NLP?

Davy Weissenbacher (1)

1 LIPN - Laboratoire d'Informatique de Paris-Nord

The NLP systems often have low perfor- mances because they rely on unreliable and heterogeneous knowledge. We show on the task of non-anaphoric it identiifi- cation how to overcome these handicaps with the Bayesian Network (BN) formal- ism. The first results are very encourag- ing compared with the state-of-the-art sys- tems.

Domaines: Traitement du texte et du document

Davy Weissenbacher. Bayesian Network, a model for NLP?. 2006, pp.195-198. ⟨hal-00095189⟩