Transfer Deep Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network

With the continuous development of information technology, word segmentation technology becomes an important link in dealing with the increasing amount of information conveniently. Different from English word segmented by spaces, Chinese writing is continuous, and there is no space between words, this brings a lot of trouble to word segmentation. In this article, through the analysis of different property of words to get a code that can be used for training and combined it with the first kind of spline weight function neural network, then by training a large number of existing rules encoding to generate a study method that can divide the statement correctly.

Download Full-text

Learning Chinese Word Segmentation Based on Bidirectional GRU-CRF and CNN Network Model

International Journal of Technology and Human Interaction ◽

10.4018/ijthi.2019070104 ◽

2019 ◽

Vol 15 (3) ◽

pp. 47-62 ◽

Cited By ~ 2

Author(s):

Chenghai Yu ◽

Shupei Wang ◽

Jiajun Guo

Keyword(s):

Neural Network ◽

Network Model ◽

Neural Network Model ◽

Network Models ◽

Word Segmentation ◽

Chinese Word ◽

Chinese Word Segmentation ◽

Neural Network Models ◽

Long Distance ◽

Training Time

Chinese word segmentation is the basis of the Chinese natural language processing (NLP). With the development of the deep learning, various neural network models are applied to the Chinese word segmentation. However, current neural network models have the characteristics of artificial feature extraction, nonstandard word-weight, inability to effectively use long-distance information and long training time of models in Chinese word segmentation. To solve a series of problems, this article presents a CNN-Bidirectional GRU-CRF neural network model (CNN Bidirectional GRU CRF Network, CBiGCN), which breaks through the limit of conventional method window, truly realizes end-to-end processing and applies to the neural network model by the five-Tag set method, bias-variable-weight greedy strategy and supplements by Goldstein-Armijo guidelines. Besides, this model, with simple structure, is easy to be operated. And it can automatically learn features, reduces large amounts of tasks on specific knowledge in the form of handcrafted features and data pre-processing, makes use of context information effectively. The authors set an experiment with two data corpuses for Chinese word segmentation to evaluate their system. The experiment verified their new model can obtain better Chinese word segmentation results and greatly reduce training time.

Download Full-text

Chinese Word Segmentation Based on Deep Learning

Proceedings of the 2018 10th International Conference on Machine Learning and Computing - ICMLC 2018 ◽

10.1145/3195106.3195135 ◽

2018 ◽

Cited By ~ 2

Author(s):

Mengge Wang ◽

Xiaoge Li ◽

Zheng Wei ◽

Shuting Zhi ◽

Haoyue Wang

Keyword(s):

Deep Learning ◽

Word Segmentation ◽

Chinese Word ◽

Chinese Word Segmentation

Download Full-text