A hybrid text normalization system using multi-head self-attention for mandarin
This work addresses text preprocessing for Mandarin, which is incremental as it builds on existing neural models to enhance traditional rule-based approaches.
The paper tackles the problem of Mandarin text normalization by proposing a hybrid system that combines rule-based and neural models, resulting in a performance improvement of over 1.5% on sentence-level accuracy.
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 1.5% on sentence-level and it has a potential to improve further.