Novel Representations of Word Embedding Based on the Zolu Function

• 作者: Jihua Lu Youcheng Zhang
• 来源期刊: 北京理工大学学报（英文版）
• 学科: 工学
• 年，卷（期）: 2020,（4）
• 页码范围: 526-530
• 页数: 5页
• 分类号: TP389.1
• 语种: 英文
• DOI: 10.15918/j.jbit1004-0579.20076

摘要

Two learning models, Zolu-continuous bags of words (ZL-CBOW) and Zolu-skip-grams (ZL-SG), based on the Zolu function are proposed. The slope of Relu in word2vec has been changed by the Zolu function. The proposed models can process extremely large data sets as well as word2vec without increasing the complexity. Also, the models outperform several word embedding methods both in word similarity and syntactic accuracy. The method of ZL-CBOW outperforms CBOW in accuracy by 8.43％ on the training set of capital-world, and by 1.24％ on the training set of plural-verbs. Moreover, experimental simulations on word similarity and syntactic accuracy show that ZL-CBOW and ZL-SG are superior to LL-CBOW and LL-SG, respectively.

作者信息

序号	姓名	单位	发文数	被引次数	H指数	G指数
1	Jihua Lu		1	0	0.0	0.0
2	Youcheng Zhang		1	0	0.0	0.0