A Hybrid Text Normalization System Using Multi-Head Self-Attention For Mandarin
Junhui Zhang, Junjie Pan, Xiang Yin, Chen Li, Shichao Liu, Yang Zhang, Yuxuan Wang, Zejun Ma
Abstract
In this paper, we propose a hybrid text normalization system using multi-head self-attention. The system combines the advantages of a rule-based model and a neural model for text preprocessing tasks. Previous studies in Mandarin text normalization usually use a set of hand-written rules, which are hard to improve on general cases. The idea of our proposed system is motivated by the neural models from recent studies and has a better performance on our internal news corpus. This paper also includes different attempts to deal with imbalanced pattern distribution of the dataset. Overall, the performance of the system is improved by over 1.9% on sentence-level. This idea can potentially be adopted by different languages with rule-based text normalization systems.
BibTeX
@inproceedings{icassp2020_ahybridtextnorma,
title = {A Hybrid Text Normalization System Using Multi-Head Self-Attention For Mandarin},
author = {Junhui Zhang and Junjie Pan and Xiang Yin and Chen Li and Shichao Liu and Yang Zhang and Yuxuan Wang and Zejun Ma},
booktitle = {ICASSP 2020},
year = {2020}
}