A Hybrid Text Normalization System Using Multi-Head Self-Attention For Mandarin
By Junhui Zhang, Junjie Pan, Xiang Yin, Chen Li, Shichao Liu, Yang Zhang, Yuxuan Wang, Zejun Ma. 2019
17 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- A Survey on Neural Speech Synthesis (2021, methodology): “In statistic parametric synthesis, text analysis is used to extract a sequence of linguistic feature vectors [351], and contains several functionalities such as text normalization [310, 432], word segmentation [394], part-of-speech (POS) tagging [292], prosody prediction [50], and grapheme-to-phonem”
- Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “[258] standardized Mandarin text by combining the traditional rule-based system with a neural text network consisting of multi-head self-attention modules in Transformer to convert Non-Standard Words (NSW) into Spoken-Form Words (SFW).”