Fast End-to-end Coreference Resolution for Korean

Cheoneum Park, Jamin Shin, Sungjoon Park, Joonho Lim, Changki Lee


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.
Anthology ID:
2020.findings-emnlp.237
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2610–2624
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.237
DOI:
10.18653/v1/2020.findings-emnlp.237
Bibkey:
Cite (ACL):
Cheoneum Park, Jamin Shin, Sungjoon Park, Joonho Lim, and Changki Lee. 2020. Fast End-to-end Coreference Resolution for Korean. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2610–2624, Online. Association for Computational Linguistics.
Cite (Informal):
Fast End-to-end Coreference Resolution for Korean (Park et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.237.pdf
Optional supplementary material:
 2020.findings-emnlp.237.OptionalSupplementaryMaterial.pdf