# Approaching Neural Chinese Word Segmentation as a Low-Resource Machine Translation Task

arXiv: https://arxiv.org/abs/2008.05348 · HTML: https://mlsanity.com/paper/2008.05348/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2020.

## Built on by (most cited first, 1 of 1)

- [Is Attention always needed? A Case Study on Language Identification from Speech](https://mlsanity.com/paper/2110.03427/) (2021)

## Abstract (arXiv)

Chinese word segmentation has entered the deep learning era which greatly reduces the hassle of feature engineering. Recently, some researchers attempted to treat it as character-level translation, which further simplified model designing, but there is a performance gap between the translation-based approach and other methods. This motivates our work, in which we apply the best practices from low-resource neural machine translation to supervised Chinese segmentation. We examine a series of techniques including regularization, data augmentation, objective weighting, transfer learning, and ensembling. Compared to previous works, our low-resource translation-based method maintains the effortless model design, yet achieves the same result as state of the art in the constrained evaluation without using additional data.