TRAPACC and TRAPACCS at PARSEME Shared Task 2018: Neural Transition Tagging of Verbal Multiword Expressions

Regina Stodden, Behrang QasemiZadeh, Laura Kallmeyer


Abstract
We describe the TRAPACC system and its variant TRAPACCS that participated in the closed track of the PARSEME Shared Task 2018 on labeling verbal multiword expressions (VMWEs). TRAPACC is a modified arc-standard transition system based on Constant and Nivre’s (2016) model of joint syntactic and lexical analysis in which the oracle is approximated using a classifier. For TRAPACC, the classifier consists of a data-independent dimension reduction and a convolutional neural network (CNN) for learning and labelling transitions. TRAPACCS extends TRAPACC by replacing the softmax layer of the CNN with a support vector machine (SVM). We report the results obtained for 19 languages, for 8 of which our system yields the best results compared to other participating systems in the closed-track of the shared task.
Anthology ID:
W18-4930
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
Venue:
LAW
SIGs:
SIGLEX | SIGANN
Publisher:
Association for Computational Linguistics
Note:
Pages:
268–274
Language:
URL:
https://aclanthology.org/W18-4930
DOI:
Bibkey:
Cite (ACL):
Regina Stodden, Behrang QasemiZadeh, and Laura Kallmeyer. 2018. TRAPACC and TRAPACCS at PARSEME Shared Task 2018: Neural Transition Tagging of Verbal Multiword Expressions. In Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), pages 268–274, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
TRAPACC and TRAPACCS at PARSEME Shared Task 2018: Neural Transition Tagging of Verbal Multiword Expressions (Stodden et al., LAW 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-4930.pdf