A Neural Graph-based Approach to Verbal MWE Identification

Jakub Waszczuk, Rafael Ehren, Regina Stodden, Laura Kallmeyer


Abstract
We propose to tackle the problem of verbal multiword expression (VMWE) identification using a neural graph parsing-based approach. Our solution involves encoding VMWE annotations as labellings of dependency trees and, subsequently, applying a neural network to model the probabilities of different labellings. This strategy can be particularly effective when applied to discontinuous VMWEs and, thanks to dense, pre-trained word vector representations, VMWEs unseen during training. Evaluation of our approach on three PARSEME datasets (German, French, and Polish) shows that it allows to achieve performance on par with the previous state-of-the-art (Al Saied et al., 2018).
Anthology ID:
W19-5113
Volume:
Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
Month:
August
Year:
2019
Address:
Florence, Italy
Venue:
MWE
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
114–124
Language:
URL:
https://aclanthology.org/W19-5113
DOI:
10.18653/v1/W19-5113
Bibkey:
Cite (ACL):
Jakub Waszczuk, Rafael Ehren, Regina Stodden, and Laura Kallmeyer. 2019. A Neural Graph-based Approach to Verbal MWE Identification. In Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), pages 114–124, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
A Neural Graph-based Approach to Verbal MWE Identification (Waszczuk et al., MWE 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5113.pdf
Code
 kawu/vine