# Attention Is All You Need for Chinese Word Segmentation

arXiv: https://arxiv.org/abs/1910.14537 · HTML: https://mlsanity.com/paper/1910.14537/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

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

- [Lingxi: A Diversity-aware Chinese Modern Poetry Generation System](https://mlsanity.com/paper/2108.12108/) (2021)
- [Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Application](https://mlsanity.com/paper/2111.09078/) (2021)

## Abstract (arXiv)

Taking greedy decoding algorithm as it should be, this work focuses on further strengthening the model itself for Chinese word segmentation (CWS), which results in an even more fast and more accurate CWS model. Our model consists of an attention only stacked encoder and a light enough decoder for the greedy segmentation plus two highway connections for smoother training, in which the encoder is composed of a newly proposed Transformer variant, Gaussian-masked Directional (GD) Transformer, and a biaffine attention scorer. With the effective encoder design, our model only needs to take unigram features for scoring. Our model is evaluated on SIGHAN Bakeoff benchmark datasets. The experimental results show that with the highest segmentation speed, the proposed model achieves new state-of-the-art or comparable performance against strong baselines in terms of strict closed test setting.