Projection Interlingue d'Étiquettes pour l'Annotation Sémantique Non Supervisée

Abstract : 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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [45 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01350117
Contributor : Laurent Besacier <>
Submitted on : Friday, July 29, 2016 - 4:28:04 PM
Last modification on : Thursday, April 4, 2019 - 10:18:05 AM
Document(s) archivé(s) le : Sunday, October 30, 2016 - 11:06:11 AM

File

T7.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01350117, version 1

Citation

Othman Zennaki, Nasredine Semmar, Laurent Besacier. Projection Interlingue d'Étiquettes pour l'Annotation Sémantique Non Supervisée. TALN 2016, Jul 2016, Paris, France. ⟨hal-01350117⟩

Share

Metrics

Record views

392

Files downloads

146