Year: 2020
Type: conference-paper
Abstract: 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.
Authors: Shyh-Shiun Hung, Hen-Hsen Huang, Hsin-Hsi Chen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G2205640134, G2270262040, Joint Research Center for AI Technology and All Vista Healthcare(3/5), Information Recall Support for Elderly People in Hyper Aged Societies, Ai Support for Social and Mental Activities of the Elderly( III ), Effective Multi-Aspects Big Data Analytics Techniques for the Economic and Commerce Trends Prediction System( III )
OpenAlex ID: W3034849249
