BriefGPT.xyz
Jul, 2017
一种用于语法错误校正的嵌套注意力神经混合模型
A Nested Attention Neural Hybrid Model for Grammatical Error Correction
HTML
PDF
Jianshu Ji, Qinlong Wang, Kristina Toutanova, Yongen Gong, Steven Truong...
TL;DR
通过基于嵌套注意力层的混合神经模型，将神经机器翻译方法发展应用于语法纠错，实验证明该模型对单词或字符水平上的错误检测和修复均具有良好的效果，并在CoNLL-14基准测试数据集上明显优于以往的神经模型，尤其对小修改的局部错误有明显的改善。
Abstract
grammatical error correction
(GEC) systems strive to correct both global errors in word order and usage, and local errors in spelling and inflection. Further developing upon recent work on
neural machine translation
→