Projection Interlingue d'Étiquettes pour l'Annotation Sémantique Non Supervisée
Résumé
Cross-lingual Annotation Projection for Unsupervised Semantic Tagging. This work focuses on the development of linguistic analysis tools for resource-poor languages. In a previous study, we proposed a method based on cross-language projection of linguistic annotations from parallel corpora to automatically induce a morpho-syntactic analyzer. Our approach was based on Recurrent Neural Networks (RNNs). In this paper, we present an improvement of our neural model. We investigate the inclusion of external information (POS tags) in the neural network to train a multilingual SuperSenses Tagger. We demonstrate the validity and genericity of our method by using parallel corpora (obtained by manual or automatic translation). Our experiments are conducted for cross-lingual annotation projection from English to French and Italian.
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...