# A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing

## TL;DR

This paper introduces a graph-based joint model for Chinese word segmentation and dependency parsing, effectively reducing error propagation and leveraging BERT to improve performance over previous methods.

## Contribution

A concise graph-based joint model that outperforms previous models and integrates BERT to close the gap with gold-standard segmentation.

## Key findings

- Achieves state-of-the-art results in Chinese word segmentation and dependency parsing.
- Reduces error propagation by integrating tasks into a single graph-based model.
- Enhances dependency parsing performance with BERT integration.

## Abstract

Chinese word segmentation and dependency parsing are two fundamental tasks for Chinese natural language processing. The dependency parsing is defined on word-level. Therefore word segmentation is the precondition of dependency parsing, which makes dependency parsing suffer from error propagation and unable to directly make use of the character-level pre-trained language model (such as BERT). In this paper, we propose a graph-based model to integrate Chinese word segmentation and dependency parsing. Different from previous transition-based joint models, our proposed model is more concise, which results in fewer efforts of feature engineering. Our graph-based joint model achieves better performance than previous joint models and state-of-the-art results in both Chinese word segmentation and dependency parsing. Besides, when BERT is combined, our model can substantially reduce the performance gap of dependency parsing between joint models and gold-segmented word-based models. Our code is publicly available at https://github.com/fastnlp/JointCwsParser.