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

Nicolas Zampieri, Manon Scholivet, Carlos Ramisch, Benoit Favre


Abstract
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.
Anthology ID:
W18-4933
Volume:
Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Venues:
COLING | LAW | MWE | WS
SIGs:
SIGLEX | SIGANN
Publisher:
Association for Computational Linguistics
Note:
Pages:
290–296
Language:
URL:
https://aclanthology.org/W18-4933
DOI:
Bibkey:
Cite (ACL):
Nicolas Zampieri, Manon Scholivet, Carlos Ramisch, and Benoit Favre. 2018. Veyn at PARSEME Shared Task 2018: Recurrent Neural Networks for VMWE Identification. In Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), pages 290–296, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Veyn at PARSEME Shared Task 2018: Recurrent Neural Networks for VMWE Identification (Zampieri et al., 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/W18-4933.pdf
Code
 zamp13/Veyn