no code implementations • 13 Mar 2024 • Ming Dong, Yujing Chen, Miao Zhang, Hao Sun, Tingting He
We found that by introducing a small number of specific Chinese rich semantic structures, LLMs achieve better performance than the BERT-based model on few-shot CSC task.
no code implementations • 13 Mar 2024 • Ming Dong, Kang Xue, Bolong Zheng, Tingting He
However, there are few methods that consider the impact of data samples on parameter selecting, such as Fish Mask based method.