Feb. 29, 2024, 5:48 a.m. | Linfeng Liu, Hongqiu Wu, Hai Zhao

cs.CL updates on arXiv.org arxiv.org

arXiv:2308.08796v3 Announce Type: replace
Abstract: This paper studies Chinese Spelling Correction (CSC), which aims to detect and correct the potential spelling errors in a given sentence. Current state-of-the-art methods regard CSC as a sequence tagging task and fine-tune BERT-based models on sentence pairs. However, we note a critical flaw in the process of tagging one character to another, that the correction is excessively conditioned on the error. This is opposite from human mindset, where individuals rephrase the complete sentence based …

abstract art arxiv bert chinese cs.cl current errors language language model paper process regard state studies tagging type

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote