Back to Search Start Over

Eval-GCSC: A New Metric for Evaluating ChatGPT's Performance in Chinese Spelling Correction

Authors :
Li, Kunting
Hu, Yong
Wang, Shaolei
Ma, Hanhan
He, Liang
Meng, Fandong
Zhou, Jie
Publication Year :
2023

Abstract

ChatGPT has demonstrated impressive performance in various downstream tasks. However, in the Chinese Spelling Correction (CSC) task, we observe a discrepancy: while ChatGPT performs well under human evaluation, it scores poorly according to traditional metrics. We believe this inconsistency arises because the traditional metrics are not well-suited for evaluating generative models. Their overly strict length and phonics constraints may lead to underestimating ChatGPT's correction capabilities. To better evaluate generative models in the CSC task, this paper proposes a new evaluation metric: Eval-GCSC. By incorporating word-level and semantic similarity judgments, it relaxes the stringent length and phonics constraints. Experimental results show that Eval-GCSC closely aligns with human evaluations. Under this metric, ChatGPT's performance is comparable to traditional token-level classification models (TCM), demonstrating its potential as a CSC tool. The source code and scripts can be accessed at https://github.com/ktlKTL/Eval-GCSC.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2311.08219
Document Type :
Working Paper