Veyn at PARSEME Shared Task 2018: Recurrent Neural Networks for VMWE Identification

Nicolas Zampieri (1) , Manon Scholivet (1) , Carlos Ramisch (1) , Benoit Favre (1)

1 TALEP - Traitement Automatique du Langage Ecrit et Parlé

This paper describes the Veyn system, submitted to the closed track of the PARSEME Shared Task 2018 on automatic identification of verbal multiword expressions (VMWEs). Veyn is based on a sequence tagger using recurrent neural networks. We represent VMWEs using a variant of the begin-inside-outside encoding scheme combined with the VMWE category tag. In addition to the system description, we present development experiments to determine the best tagging scheme. Veyn is freely available, covers 19 languages, and was ranked ninth (MWE-based) and eight (Token-based) among 13 submissions, considering macro-averaged F1 across languages.

Domaines: Informatique et langage [cs.CL]

Nicolas Zampieri, Manon Scholivet, Carlos Ramisch, Benoit Favre. Veyn at PARSEME Shared Task 2018: Recurrent Neural Networks for VMWE Identification. Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), 2018, Santa Fe, NM, United States. ⟨hal-03619093⟩