| Li Yan (李岩),Zhang Yinghua,Huang Xiaoping,Yin Xucheng,Hao Hongwei.[J].高技术通讯(英文),2015,21(1):71~77 |
|
| Chinese word segmentation with local and global context representation learning |
| |
| DOI：10.3772/j.issn.1006-6748.2015.01.010 |
| 中文关键词: |
| 英文关键词: local and global context, representation learning, Chinese character representation, Chinese word segmentation |
| 基金项目: |
| Author Name | Affiliation | | Li Yan (李岩) | | | Zhang Yinghua | | | Huang Xiaoping | | | Yin Xucheng | | | Hao Hongwei | |
|
| Hits: 850 |
| Download times: 697 |
| 中文摘要: |
| |
| 英文摘要: |
| A local and global context representation learning model for Chinese characters is designed and a Chinese word segmentation method based on character representations is proposed in this paper. First, the proposed Chinese character learning model uses the semantics of local context and global context to learn the representation of Chinese characters. Then, Chinese word segmentation model is built by a neural network, while the segmentation model is trained with the character representations as its input features. Finally, experimental results show that Chinese character representations can effectively learn the semantic information. Characters with similar semantics cluster together in the visualize space. Moreover, the proposed Chinese word segmentation model also achieves a pretty good improvement on precision, recall and f-measure. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
