.png){kind=icon}
.png){kind=icon}
Return
Correct like humans: Progressive learning framework for Chinese text error correction
.png){kind=icon}
OA
AI
DOI：10.1016/j.eswa.2024.126039.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Chinese Text Error Correction (CTEC) aims to detect and correct errors in the input text, which benefits human daily life and various downstream tasks. With the extensive research on Pre-trained Language Models (PLMs), Chinese Spelling Correction (CSC) and Chinese Grammatical Error Correction (CGEC), two subtasks of CTEC, have achieved good results. However, researchers usually study these two tasks separately. In addition, we argue that previous studies still overlook the importance of human thinking patterns. To enhance the development of PLMs for CTEC, inspired by humans' daily error-correcting behavior, we propose a novel model-agnostic progressive learning framework, named ProTEC, which guides PLMs-based CTEC models to learn to correct like humans and can be applied to various existing CTEC models in both CSC and CGEC. During the training process, ProTEC guides the model to learn text error correction by incorporating these sub-tasks into a progressive paradigm. During the inference process, the model completes these sub-tasks in turn to generate the correction results. Extensive experiments and detailed analyses demonstrate the effectiveness and efficiency of our proposed model-agnostic ProTEC framework.
Keywords:
Chinese text error correction
Progressive learning
Natural language processing
Computational linguistics
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W
Organization
No organization information available