MCTS: A Multi-Reference Chinese Text Simplification Dataset

TL;DR

This paper introduces MCTS, a comprehensive multi-reference dataset for Chinese text simplification, facilitating evaluation and advancing research in this underexplored area.

Contribution

It provides the first large-scale Chinese text simplification dataset with multi-reference annotations and baseline evaluations using various models.

Findings

Unsupervised methods show limited performance on Chinese simplification.

Large language models outperform traditional unsupervised approaches.

The dataset enables better benchmarking for Chinese text simplification.

Abstract

Text simplification aims to make the text easier to understand by applying rewriting transformations. There has been very little research on Chinese text simplification for a long time. The lack of generic evaluation data is an essential reason for this phenomenon. In this paper, we introduce MCTS, a multi-reference Chinese text simplification dataset. We describe the annotation process of the dataset and provide a detailed analysis. Furthermore, we evaluate the performance of several unsupervised methods and advanced large language models. We additionally provide Chinese text simplification parallel data that can be used for training, acquired by utilizing machine translation and English text simplification. We hope to build a basic understanding of Chinese text simplification through the foundational work and provide references for future research. All of the code and data are released at https://github.com/blcuicall/mcts/.