# An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer

arXiv: https://arxiv.org/abs/2203.16954 · HTML: https://mlsanity.com/paper/2203.16954/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [Character-Level Language Modeling with Deeper Self-Attention](https://mlsanity.com/paper/1808.04444/) (2018)
- [Chinese NER Using Lattice LSTM](https://mlsanity.com/paper/1805.02023/) (2018)
- [FLAT: Chinese NER Using Flat-Lattice Transformer](https://mlsanity.com/paper/2004.11795/) (2020)
- [RNN Approaches to Text Normalization: A Challenge](https://mlsanity.com/paper/1611.00068/) (2016)
- [A hybrid text normalization system using multi-head self-attention for mandarin](https://mlsanity.com/paper/1911.04128/) (2019)

## Built on by (most cited first, 2 of 2)

- [CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation](https://mlsanity.com/paper/2606.24714/) (2026)
- [ASR-Roundtrip Evaluation Can Mask Context- and Convention-Dependent Reading Errors in Chinese News TTS](https://mlsanity.com/paper/2608.10606/) (2026)

## Abstract (arXiv)

Text normalization, defined as a procedure transforming non standard words to spoken-form words, is crucial to the intelligibility of synthesized speech in text-to-speech system. Rule-based methods without considering context can not eliminate ambiguation, whereas sequence-to-sequence neural network based methods suffer from the unexpected and uninterpretable errors problem. Recently proposed hybrid system treats rule-based model and neural model as two cascaded sub-modules, where limited interaction capability makes neural network model cannot fully utilize expert knowledge contained in the rules. Inspired by Flat-LAttice Transformer (FLAT), we propose an end-to-end Chinese text normalization model, which accepts Chinese characters as direct input and integrates expert knowledge contained in rules into the neural network, both contribute to the superior performance of proposed model for the text normalization task. We also release a first publicly accessible largescale dataset for Chinese text normalization. Our proposed model has achieved excellent results on this dataset.