A Complete Shift-Reduce Chinese Discourse Parser with Robust Dynamic Oracle
Shyh-Shiun Hung, Hen‐Hsen Huang, Hsin‐Hsi Chen · 2020
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.