Error-specific accuracy comparison results.

<div><p>The new progress of deep learning and natural language processing technology has strongly promoted the development of English grammar error correction. However, the existing methods mostly rely on large-scale corpus, and often ignore the fine syntactic correlation in paragraphs,...

Full description

Saved in:

Bibliographic Details
Main Author:	Weiling Liu (1465480) (author)
Other Authors:	Caijun Zhao (6741056) (author), Yongyi Li (11242842) (author), Chenglong Cai (20330541) (author), Hong Liu (50694) (author), Ruilin Qiu (21728693) (author), Ruoci Su (21728696) (author), Bingbing Li (461702) (author)
Published:	2025
Subjects:	Neuroscience Mental Health Biological Sciences not elsewhere classified sentence vector representation preliminary results show original sentence vector grammar error recognition fce data set significant differences caused difference fusion analysis seq2seq model based generate correction suggestions fine syntactic correlation grammatical errors according level grammar correction syntactic differences higher level differential fusion model focuses baseline model syntactic structure syntactic features xlink "> wrong area writing ability strongly promoted significantly better scale corpus reaching significance preset threshold powerful approach often ignore obvious advantages new progress lcole dataset key value excellent effect english writing dependency parsing deep learning cosine similarity cola dataset attention mechanism also highlights adjacent sentences
Tags:	Add Tag No Tags, Be the first to tag this record!

Error-specific accuracy comparison results.

Similar Items