Bridging the Gap: Attending to Discontinuity in Identification of Multiword Expressions [article]

Omid Rohanian, Shiva Taslimipoor, Samaneh Kouchaki, Le An Ha, Ruslan Mitkov
2019 arXiv   pre-print
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
more » ... 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.
arXiv:1902.10667v2 fatcat:j3gvtea26fg7jlihlgslxt75lq