Skip to content
conftrace_
2020 AACL AACL 2020

TMU-NLP System Using BERT-based Pre-trained Model to the NLP-TEA CGED Shared Task 2020

Abstract

AbstractIn this paper, we introduce our system for NLPTEA 2020 shared task of Chinese Grammatical Error Diagnosis (CGED). In recent years, pre-trained models have been extensively studied, and several downstream tasks have benefited from their utilization. In this study, we treat the grammar error diagnosis (GED) task as a grammatical error correction (GEC) problem and propose a method that incorporates a pre-trained model into an encoder-decoder model to solve this problem.

🚀 Conference Pioneer - AACL 2020
🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Hongfei Wang, Mamoru Komachi

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Generation > Text Generation Machine Learning > Learning Types > Transfer Learning Deep Learning > Learning Types > Transfer Learning

Keywords

transfer learning grammatical error correction text generation pre-trained model pre-trained language model encoder-decoder model chinese language
Download PDF

More from AACL 2020

All AACL 2020 papers →
BERT Enhanced Neural Machine Translation and Sequence Tagging Model for Chinese Grammatical Error Diagnosis
A Hybrid System for NLPTEA-2020 CGED Shared Task
Chinese Grammatical Error Correction Based on Hybrid Models with Data Augmentation
CYUT Team Chinese Grammatical Error Diagnosis System Report in NLPTEA-2020 CGED Shared Task
Chinese Grammatical Error Diagnosis Based on RoBERTa-BiLSTM-CRF Model
Chinese Grammatical Errors Diagnosis System Based on BERT at NLPTEA-2020 CGED Shared Task