Paper Info
Title
Fast End-to-end Coreference Resolution for Korean.
Abstract
Recently, end-to-end neural network-based approaches have shown significant improvements over traditional pipeline-based models in English coreference resolution. However, such advancements came at a cost of computational complexity and recent works have not focused on tackling this problem. Hence, in this paper, to cope with this issue, we propose BERT-SRU-based Pointer Networks that leverages the linguistic property of head-final languages. Applying this model to the Korean coreference resolution, we significantly reduce the coreference linking search space. Combining this with Ensemble Knowledge Distillation, we maintain state-of-the-art performance 66.9% of CoNLL F1 on ETRI test set while achieving 2x speedup (30 doc/sec) in document processing time.
Year
DOI
Venue
2020
10.18653/V1/2020.FINDINGS-EMNLP.237
EMNLP
DocType
Volume
Citations 
Conference
2020.findings-emnlp
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
Cheon-Eum Park113.05
Jamin Shin292.84
Sungjoon Park3194.43
Joonho Lim400.34
Changki Lee527926.18