Bridging the Gap: Attending to Discontinuity in Identification of Multiword Expressions
This work addresses a specific challenge in computational linguistics (discontinuous MWEs) for natural language processing applications, representing an incremental improvement over existing methods.
The authors tackled the problem of identifying discontinuous multiword expressions (MWEs) by proposing a linguistically interpretable deep learning architecture that combines graph convolutional networks and multi-head self-attention. Their model outperformed baselines on a standard multilingual dataset, achieving higher F-scores for both discontinuous and overall MWE identification.
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.