no code implementations • CCL 2020 • Shengsheng Zhang, Guina Pang, Liner Yang, Chencheng Wang, Yongping Du, Erhong Yang, Yaping Huang
语法纠错任务旨在通过自然语言处理技术自动检测并纠正文本中的语序、拼写等语法错误。当前许多针对汉语的语法纠错方法已取得较好的效果, 但往往忽略了学习者的个性化特征, 如二语等级、母语背景等。因此, 本文面向汉语作为第二语言的学习者, 提出个性化语法纠错, 对不同特征的学习者所犯的错误分别进行纠正, 并构建了不同领域汉语学习者的数据集进行实验。实验结果表明, 将语法纠错模型适应到学习者的各个领域后, 性能得到明显提升。
no code implementations • 29 Jan 2021 • Shengsheng Zhang, Yaping Huang, Yun Chen, Liner Yang, Chencheng Wang, Erhong Yang
We exploit a set of data-rich source domains to learn the initialization of model parameters that facilitates fast adaptation on new resource-poor target domains.
no code implementations • 29 Sep 2019 • Liner Yang, Chencheng Wang, Yun Chen, Yongping Du, Erhong Yang
We propose two data synthesis methods which can control the error rate and the ratio of error types on synthetic data.
no code implementations • WS 2019 • Liner Yang, Chencheng Wang
On the test data of the BEA 2019 Shared Task, our system yields F0. 5 = 58. 62 and 59. 50, ranking twelfth and fourth respectively.