CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora

S. David Hernandez, Hiram Calvo

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

10 Citas (Scopus)

Resumen

We describe our approach to grammatical error correction presented in the CoNLL Shared Task 2014. Our work is focused on error detection in sentences with a language model based on syntactic tri-grams and bi-grams extracted from dependency trees generated from 90% of the English Wikipedia. Also, we add a naïve module to error correction that outputs a set of possible answers, those sentences are scored using a syntactic n-gram language model. The sentence with the best score is the final suggestion of the system. The system was ranked 11th, evidently this is a very simple approach, but since the beginning our main goal was to test the syntactic n-gram language model with a big corpus to future comparison.

Idioma originalInglés
Título de la publicación alojadaCoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task
EditorialAssociation for Computational Linguistics (ACL)
Páginas53-59
Número de páginas7
ISBN (versión digital)9781941643198
EstadoPublicada - 2014
Evento18th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2014 - Baltimore, Estados Unidos
Duración: 26 jun. 201427 jun. 2014

Serie de la publicación

NombreCoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings of the Shared Task

Conferencia

Conferencia18th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2014
País/TerritorioEstados Unidos
CiudadBaltimore
Período26/06/1427/06/14

Huella

Profundice en los temas de investigación de 'CoNLL 2014 shared task: Grammatical error correction with a syntactic N-gram language model from a big corpora'. En conjunto forman una huella única.

Citar esto