Chinese Grammatical Correction Using BERT-based Pre-trained Model

11/04/2020

∙

In recent years, pre-trained models have been extensively studied, and several downstream tasks have benefited from their utilization. In this study, we verify the effectiveness of two methods that incorporate a BERT-based pre-trained model developed by Cui et al. (2020) into an encoder-decoder model on Chinese grammatical error correction tasks. We also analyze the error type and conclude that sentence-level errors are yet to be addressed.

READ FULL TEXT

Chinese Grammatical Correction Using BERT-based Pre-trained Model

Pre-trained Model for Chinese Word Segmentation with Meta Learning

Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction

A Method to Judge the Style of Classical Poetry Based on Pre-trained Model

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition

MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model

Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition

Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data

Chinese Grammatical Correction Using BERT-based Pre-trained Model

Related Research

Pre-trained Model for Chinese Word Segmentation with Meta Learning

Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction

A Method to Judge the Style of Classical Poetry Based on Pre-trained Model

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition

MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model

Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition

Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data