Dependency Parsing with Dilated Iterated Graph CNNs

Emma Strubell, Andrew McCallum


Abstract
Dependency parses are an effective way to inject linguistic knowledge into many downstream tasks, and many practitioners wish to efficiently parse sentences at scale. Recent advances in GPU hardware have enabled neural networks to achieve significant gains over the previous best models, these models still fail to leverage GPUs’ capability for massive parallelism due to their requirement of sequential processing of the sentence. In response, we propose Dilated Iterated Graph Convolutional Neural Networks (DIG-CNNs) for graph-based dependency parsing, a graph convolutional architecture that allows for efficient end-to-end GPU parsing. In experiments on the English Penn TreeBank benchmark, we show that DIG-CNNs perform on par with some of the best neural network parsers.
Anthology ID:
W17-4301
Volume:
Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Kai-Wei Chang, Ming-Wei Chang, Vivek Srikumar, Alexander M. Rush
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–6
Language:
URL:
https://aclanthology.org/W17-4301
DOI:
10.18653/v1/W17-4301
Bibkey:
Cite (ACL):
Emma Strubell and Andrew McCallum. 2017. Dependency Parsing with Dilated Iterated Graph CNNs. In Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing, pages 1–6, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Dependency Parsing with Dilated Iterated Graph CNNs (Strubell & McCallum, 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-4301.pdf