2020.acl-main.13@ACL

Total: 1

#1 A Complete Shift-Reduce Chinese Discourse Parser with Robust Dynamic Oracle [PDF] [Copy] [Kimi1] [REL]

Authors: Shyh-Shiun Hung, Hen-Hsen Huang, Hsin-Hsi Chen

This work proposes a standalone, complete Chinese discourse parser for practical applications. We approach Chinese discourse parsing from a variety of aspects and improve the shift-reduce parser not only by integrating the pre-trained text encoder, but also by employing novel training strategies. We revise the dynamic-oracle procedure for training the shift-reduce parser, and apply unsupervised data augmentation to enhance rhetorical relation recognition. Experimental results show that our Chinese discourse parser achieves the state-of-the-art performance.