Bayesian Network, a Model for NLP?

The NLP systems often have low performances because they rely on unreliable and heterogeneous knowledge. We show on the task of non-anaphoric it identification how to overcome these handicaps with the Bayesian Network (BN) formalism. The first results are very encouraging compared with the state-of-the-art systems.

• Type: Conference
• Year: 2006
• Where: EACL
• Authors: Davy Weissenbacher
• Keywords: EACL 2006, Heterogeneous Knowledge, Low Performances, Natural Language Processing, NLP Systems