Repository logo
 

Bridging the gap: Attending to discontinuity in identification of multiword expressions

Published version
Peer-reviewed

Type

Conference Object

Change log

Authors

Rohanian, O 
Taslimipoor, S 
Kouchaki, S 
Ha, LA 
Mitkov, R 

Abstract

We introduce a new method to tag Multiword Expressions (MWEs) using a linguistically interpretable language-independent deep learning architecture. We specifically target discontinuity, an under-explored aspect that poses a significant challenge to computational treatment of MWEs. Two neural architectures are explored: Graph Convolutional Network (GCN) and multi-head self-attention. GCN leverages dependency parse information, and self-attention attends to long-range relations. We finally propose a combined model that integrates complementary information from both through a gating mechanism. The experiments on a standard multilingual dataset for verbal MWEs show that our model outperforms the baselines not only in the case of discontinuous MWEs but also in overall F-score.

Description

Keywords

cs.CL, cs.CL, cs.AI

Journal Title

NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference

Conference Name

Proceedings of the 2019 Conference of the North

Journal ISSN

Volume Title

1

Publisher

Association for Computational Linguistics