Loading...
Bridging the gap: attending to discontinuity in identification of multiword expressions
Rohanian, Omid Taslimipoor, Shiva Kouchaki, Samaneh Ha, Le An Mitkov, Ruslan
Rohanian, Omid
Taslimipoor, Shiva
Kouchaki, Samaneh
Ha, Le An
Mitkov, Ruslan
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2019-06-05
Submitted date
Alternative
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.
Citation
Rohanian, O., Taslimipoor, S., Kouchaki, S., Ha, L. A. and Mitkov, R. (2019) Bridging the gap: attending to discontinuity in identification of multiword expressions, in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Minneapolis, Minnesota: Association for Computational Linguistics, pp. 2692–2698.
Journal
Research Unit
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
Type
Conference contribution
Language
en
Description
Series/Report no.
ISSN
EISSN
ISBN
ISMN
Gov't Doc #
Sponsors
Rights
Attribution-NonCommercial-NoDerivs 3.0 United States