Title

NLP-enhanced error Checking for Catalan unrestricted text

Author(s)

Toni Badia, Àngel Gil, Martí Quixal, Oriol Valentín

GLiCom, Universitat Pompeu Fabra

Session

P23-W

Abstract

We present here a general-purpose spell and grammar error detection architecture for Catalan unrestricted text. This architecture is based on a previous existing shallow morphosyntactic parser, which had to be adapted in order to successfully handle ill-formed input. The goal of this research is to obtain an architecture that can be used for developing morphosyntactic error checkers for both native and non-native speakers. We briefly present how we are currently customizing such an architecture in two different projects, as well as a means for annotating and exploiting error corpora (which ultimately condition the implementation of error checkers). We conclude with some remarks and future work.

Keyword(s)

error detection, NLP processing, language learning

Language(s) Catalan (and Spanish)
Full Paper

260.pdf