干旱区生态环境知识资源中心(Arid): Attention-based Multi-layer Chinese Word Embedding

Arid

	Attention-based Multi-layer Chinese Word Embedding
	Ma, Bing; Sun, Haifeng; Wang, Jingyu; Qi, Qi
通讯作者	Ma, B (corresponding author), State Key Lab Networking & Switching Technol, Beijing, Peoples R China. ; Ma, B (corresponding author), Beijing Univ Posts & Telecommun, Beijing, Peoples R China.
会议名称	IEEE International Conference on Big Data (Big Data)
会议日期	DEC 09-12, 2019
会议地点	Los Angeles, CA
英文摘要	Word embedding is a basic task in natural language processing area. Unlike English, Chinese subword units, such as characters, radicals, and components, contain rich semantic information which can be used to enhance word embeddings. However, existing methods neglect the semantic contribution of corresponding subword units to the word. In this work, we employ attention mechanism to capture the semantic structure of Chinese words and propose a novel framework, named Attention-based multi-Layer Word Embedding model(ALWE). We also design an asynchronous strategy for updating embedding arid attention efficiently. Our model learns to share subword information between distinct words selectively and adaptively. Experimental results on the word similarity, word analogy, and text classification show that the proposed model outperforms all baselines, especially when words don't appear frequently. Qualitative analysis further demonstrates the superiority of ALWE.
英文关键词	distributed word representation attention mechanism Chinese semantic structure
来源出版物	2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)
ISSN	2639-1589
出版年	2019
页码	2895-2902
ISBN	978-1-7281-0858-2
出版者	IEEE
类型	Proceedings Paper
语种	英语
收录类别	CPCI-S
WOS记录号	WOS:000554828702114
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Computer Science, Theory & Methods
WOS研究方向	Computer Science
资源类型	会议论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/369984
作者单位	[Ma, Bing; Sun, Haifeng; Wang, Jingyu; Qi, Qi] State Key Lab Networking & Switching Technol, Beijing, Peoples R China; [Ma, Bing; Sun, Haifeng; Wang, Jingyu; Qi, Qi] Beijing Univ Posts & Telecommun, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ma, Bing,Sun, Haifeng,Wang, Jingyu,et al. Attention-based Multi-layer Chinese Word Embedding[C]:IEEE,2019:2895-2902.