To improve the performance of Chinese new words detection, this paper enhances the traditional method through two aspects. Firstly, a new and more effective ...

Based on the above analysis, this paper proposes an unsu- pervised new words detection method with enhanced branch entropy. Besides, n-gram segmentation ...

Abstract: As a basic task of Chinese natural language processing,new word detection is crucial for improving the performance of various downstream tasks.

A multimodal method for Chinese spelling correction. G Zhao, Y Guo, F Xia, C Ma ... An Improved Branch Entropy Based Method for Chinese New Words Detection. Y ...

This work proposes a joint statistical model to perform the extraction of domain-specific new words automatically in Chinese and demonstrates that the joint ...

The experimental results show that our proposed method is effective for correctly segmenting most Classical Chinese sentences in Buddhist literature. Our word ...

In the experiment, we found that our method can achieve better detection performance in low-entropy scenarios, and our method is also general and can be applied ...

May 11, 2023 · However, there are very few published datasets for CTAS. This paper introduces a new benchmark dataset for the task of CTAS to promote ...

Apr 25, 2023 · Branch entropy is used to calculate the probabilities between words. Finally, the N-gram algorithm is used to segment the preprocessed corpus.

Abstract— This paper proposes a new word discovery algorithm based on mutual information and branch entropy in order to solve the problems of fast updating ...