CCG Supertagging Using Morphological and Dependency Syntax Information

Abstract : After presenting a new CCG supertagging algorithm based on morphological and dependency syntax information, we use this algorithm to create a CCG French Tree Bank corpus (20,261 sentences) based on the FTB corpus by Abeillé et al. We then use this corpus, as well as the Groningen Tree Bank corpus for the English language, to train a new BiLSTM+CRF neural architecture that uses (a) morphosyntactic input features and (b) feature correlations as input features. We show experimentally that for an inflected language like French, dependency syntax information allows significant improvement of the accuracy of the CCG supertagging task, when using deep learning techniques.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02110790
Contributor : Bibliothèque Télécom Bretagne <>
Submitted on : Friday, April 26, 2019 - 1:08:58 PM
Last modification on : Tuesday, May 28, 2019 - 5:14:03 PM

File

CCG_Supertagging (2).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02110790, version 1

Citation

Ngoc Luyen Le, Yannis Haralambous. CCG Supertagging Using Morphological and Dependency Syntax Information. International Conference on Computational Linguistics and Intelligent Text Processing, Apr 2019, La Rochelle, France. ⟨hal-02110790⟩

Share

Metrics

Record views

29

Files downloads

26