Using Universal Dependencies in cross-linguistic complexity research - Université Paris Nanterre
Chapitre D'ouvrage Année : 2018

Using Universal Dependencies in cross-linguistic complexity research

Résumé

We evaluate corpus-based measures of linguistic complexity obtained using Universal Dependencies (UD) treebanks. We propose a method of estimating robustness of the complexity values obtained using a given measure and a given treebank. The results indicate that measures of syntactic complexity might be on average less robust than those of morphological complexity. We also estimate the validity of complexity measures by comparing the results for very similar languages and checking for unexpected differences. We show that some of those differences that arise can be diminished by using parallel treebanks and, more importantly from the practical point of view, by harmonizing the languagespecific solutions in the UD annotation.

Dates et versions

hal-04088452 , version 1 (04-05-2023)

Identifiants

Citer

Aleksandrs Berdicevskis, Çağrı Çöltekin, Katharina Ehret, Kilu von Prince, Daniel Ross, et al.. Using Universal Dependencies in cross-linguistic complexity research. Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), Association for Computational Linguistics, pp.8-17, 2018, ⟨10.18653/v1/W18-6002⟩. ⟨hal-04088452⟩
12 Consultations
0 Téléchargements

Altmetric

Partager

More