A transition-based verbal multiword expression analyzer
Abstract
We describe a robust transition-based analyzer for identifying and categorizing Verbal Multiword Expressions (VMWEs). The system was developed and evaluated using the datasets of the PARSEME shared task on VMWE identification (Savary et al. 2017). We accommodate the variety of linguistic resources provided for each language, in terms of accompanying morphological and syntactic information. Our system produces very competitive scores, for both VMWE identification and categorization, with respect to the shared task results.
Domains
Document and Text Processing
Fichier principal
Multiword expressions at length and in depth.pdf (241.94 Ko)
Télécharger le fichier
Origin | Publication funded by an institution |
---|