Results 261 to 270 of about 284,138 (314)

gec-metrics: A Unified Library for Grammatical Error Correction Evaluation

Annual Meeting of the Association for Computational Linguistics
We introduce gec-metrics, a library for using and developing grammatical error correction (GEC) evaluation metrics through a unified interface. Our library enables fair system comparisons by ensuring that everyone conducts evaluations using a consistent ...
Takumi Goto, Yusuke Sakai, Taro Watanabe
semanticscholar   +1 more source

Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study

Annual Meeting of the Association for Computational Linguistics
Text editing frames grammatical error correction (GEC) as a sequence tagging problem, where edit tags are assigned to input tokens, and applying these edits results in the corrected text.
Bashar Alhafni, Nizar Habash
semanticscholar   +1 more source

Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?

Annual Meeting of the Association for Computational Linguistics
One of the goals of automatic evaluation metrics in grammatical error correction (GEC) is to rank GEC systems such that it matches human preferences.
Takumi Goto, Yusuke Sakai, Taro Watanabe
semanticscholar   +1 more source

Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correction

arXiv.org
Grammatical Error Correction (GEC) faces a critical challenge concerning explainability, notably when GEC systems are designed for language learners.
Jingheng Ye, S. Qin, Yinghui Li, Hai-Tao Zheng, Shen Wang, Qingsong Wen   +5 more
semanticscholar   +1 more source

Exploring the Feasibility of Multilingual Grammatical Error Correction with a Single LLM up to 9B parameters: A Comparative Study of 17 Models

arXiv.org
Recent language models can successfully solve various language-related tasks, and many understand inputs stated in different languages. In this paper, we explore the performance of 17 popular models used to correct grammatical issues in texts stated in ...
Dawid Wisniewski, Antoni Solarski, Artur Nowakowski   +2 more
semanticscholar   +1 more source

ScholarGEC: Enhancing Controllability of Large Language Model for Chinese Academic Grammatical Error Correction

AAAI Conference on Artificial Intelligence
Large language models (LLMs) have demonstrated exceptional error detection capabilities and can correct sentences with high fluency in grammatical error correction (GEC) tasks.
Zixiao Kong, Xianquan Wang, Shuanghong Shen, Keyu Zhu, Huibo Xu, Yu Su   +5 more
semanticscholar   +1 more source

Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction

Interspeech
Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipeline consisting of an ASR, a module for disfluency detection (DD) and ...
Mengjie Qian, Rao Ma, Stefano Bannò, K. Knill, Mark Gales   +4 more
semanticscholar   +1 more source

Hybrid LLM and Rule-Based Synthetic Data Generation for Arabic Grammatical Error Correction

2025 International Conference on Machine Intelligence and Smart Innovation (ICMISI)
The correction of Arabic grammatical errors has re-cently gained interest due to the emergence of strong transformer models trained on internet-scale Arabic data and large language models capable of generalizing well to new tasks and languages.
Mohamed Abdelrehim, Marwan Torki, Nagwa M. El-Makky   +2 more
semanticscholar   +1 more source

Adapting LLMs for Minimal-edit Grammatical Error Correction

Workshop on Innovative Use of NLP for Building Educational Applications
Decoder-only large language models have shown superior performance in the fluency-edit English Grammatical Error Correction, but their adaptation for minimal-edit English GEC is still underexplored.
Ryszard Staruch, Filip Grali'nski, Daniel Dzienisiewicz   +2 more
semanticscholar   +1 more source

Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction

North American Chapter of the Association for Computational Linguistics
Grammatical error correction (GEC) aims to correct grammatical, spelling, and semantic errors in natural language text. With the growing of large language models (LLMs), direct text generation has gradually become the focus of the GEC methods, and few ...
Wei Li, Wen Luo, Guangyue Peng, Houfeng Wang   +3 more
semanticscholar   +1 more source