# Fast and Accurate Neural Word Segmentation for Chinese

arXiv: https://arxiv.org/abs/1704.07047 · HTML: https://mlsanity.com/paper/1704.07047/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2017.

## Built on by (most cited first, 3 of 3)

- [Joint Optimization of Tokenization and Downstream Model](https://mlsanity.com/paper/2105.12410/) (2021)
- [Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling](https://mlsanity.com/paper/2104.07704/) (2021)
- [Moto: Enhancing Embedding with Multiple Joint Factors for Chinese Text Classification](https://mlsanity.com/paper/2212.08105/) (2022)

## Abstract (arXiv)

Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation. However, both training and working procedures of the current neural models are computationally inefficient. This paper presents a greedy neural word segmenter with balanced word and character embedding inputs to alleviate the existing drawbacks. Our segmenter is truly end-to-end, capable of performing segmentation much faster and even more accurate than state-of-the-art neural models on Chinese benchmark datasets.