Clues to compare languages for morphosyntactic analysis: a study run on parallel corpora and morphosyntactic lexicons

Authors:
Helena Blancafort;Claude de Loupy
Affiliations:
Syllabs, 15, rue Jean-Baptiste Berlier, Paris, France and Universitat Pompeu Fabra, Roc Boronat, Barcelona, Spain;Syllabs, 15, rue Jean-Baptiste Berlier, Paris, France
Venue:
LTC'09 Proceedings of the 4th conference on Human language technology: challenges for computer science and linguistics
Year:
2009

Citing 4
Cited 0

Multilevel decoding for very-large-size-dictionary speech recognition

IBM Journal of Research and Development
Unsupervised learning of the morphology of a natural language

Computational Linguistics
MULTEXT: Multilingual Text Tools and Corpora

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
Analysis of EU languages through text compression

FinTAL'06 Proceedings of the 5th international conference on Advances in Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The aim of the present work is to find clues on how to compare the difficulties of five languages for morphosyntactic analysis and the development of lexicographic resources running a corpora and lexical comparative study on multilingual parallel corpora and morphosyntactic lexicons. First, we ran some corpus-based experiments without any other type of knowledge, following classical measures used in lexical statistics. Then we carried out further experiments on the corpora using morphosyntactic lexicons. Finally, we plotted given diagrams using different clues to offer an overview of the difficulty of a language for the development of morphosyntactic resources.