Grammatical Error Correction
Grammatical error correction (GEC) aims to automatically identify and rectify grammatical mistakes in text, primarily focusing on improving accuracy and fluency. Current research heavily utilizes large language models (LLMs) within various architectures, including sequence-to-sequence and non-autoregressive models, often employing techniques like data augmentation and multi-task learning to enhance performance. This field is significant for its potential to improve language learning tools, automate writing assistance, and advance the understanding of both human language and artificial intelligence evaluation methods. Furthermore, the development of robust evaluation metrics, including those leveraging LLMs themselves, is a key area of ongoing investigation.
Papers
Improving Explainability of Sentence-level Metrics via Edit-level Attribution for Grammatical Error Correction
Takumi Goto, Justin Vasselli, Taro Watanabe
DSGram: Dynamic Weighting Sub-Metrics for Grammatical Error Correction in the Era of Large Language Models
Jinxiang Xie, Yilin Li, Xunjian Yin, Xiaojun Wan
LLMCL-GEC: Advancing Grammatical Error Correction with LLM-Driven Curriculum Learning
Tao Fang, Derek F. Wong, Lusheng Zhang, Keyan Jin, Qiang Zhang, Tianjiao Li, Jinlong Hou, Lidia S. Chao
CLEME2.0: Towards More Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction
Jingheng Ye, Zishan Xu, Yinghui Li, Xuxin Cheng, Linlin Song, Qingyu Zhou, Hai-Tao Zheng, Ying Shen, Xin Su
EXCGEC: A Benchmark of Edit-wise Explainable Chinese Grammatical Error Correction
Jingheng Ye, Shang Qin, Yinghui Li, Xuxin Cheng, Libo Qin, Hai-Tao Zheng, Peng Xing, Zishan Xu, Guo Cheng, Zhao Wei