Y Fan, F Jiang, P Li, H Li - … on Natural Language Processing and Chinese …, 2023 - Springer
Grammatical error correction aims to correct ungrammatical sentences automatically. Recently, some work has demonstrated the excellent capabilities of closed-source Large …
Y Li, S Ma, S Chen, H Huang, S Huang… - Available at SSRN …, 2023 - papers.ssrn.com
Abstract Chinese Text Error Correction (CTEC) aims to detect and correct errors in the input text, which benefits human daily life and various downstream tasks. Recent approaches …
Text error correction aims to correct the errors in text sequences such as those typed by humans or generated by speech recognition models. Previous error correction methods …
We introduce NaSGEC, a new dataset to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains. Previous CGEC research …
Y Zhang, Y Zhang, L Cui, G Fu - arXiv preprint arXiv:2310.07821, 2023 - arxiv.org
Recent work has witnessed a paradigm shift from Seq2Seq to Seq2Edit in the field of text editing, with the aim of addressing the slow autoregressive inference problem posed by the …
X Wu, Y Wu - arXiv preprint arXiv:2211.01625, 2022 - arxiv.org
Chinese Grammatical Error Correction (CGEC) aims to generate a correct sentence from an erroneous sequence, where different kinds of errors are mixed. This paper divides the …
AI has introduced a new reform direction for traditional education, such as automating Grammatical Error Correction (GEC) to reduce teachers' workload and improve efficiency …
K Al-Sabahi, K Yang, W Liu, G Jiang, X Li… - … Applications of Artificial …, 2024 - Elsevier
Abstract To solve the Grammatical Error Correction (GEC) problem, a mapping between a source sequence and a target one is needed, where the two differ only on few spans. For …
N Shi, B Tang, B Yuan, L Huang, Y Pu, J Fu… - arXiv preprint arXiv …, 2022 - arxiv.org
Text editing, such as grammatical error correction, arises naturally from imperfect textual data. Recent works frame text editing as a multi-round sequence tagging task, where …