Sorry, you need to enable JavaScript to visit this website.

A HYBRID TEXT NORMALIZATION SYSTEM USING MULTI-HEAD SELF-ATTENTION FOR MANDARIN

Citation Author(s):
Junhui Zhang, Junjie Pan, Xiang Yin, Chen Li, Shichao Liu, Yang Zhang, Yuxuan Wang, Zejun Ma
Submitted by:
Junhui Zhang
Last updated:
13 May 2020 - 10:27pm
Document Type:
Presentation Slides
Document Year:
2020
Event:
Presenters:
Junhui Zhang
Paper Code:
SPE-P3.3
 

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.

up
0 users have voted: