Feature-Frequency-Adaptive On-line Training for Fast and Accurate   Natural Language Processing

doi:10.1162/COLI_a_00193

CORC > 北京大学 > 信息科学技术学院

	Feature-Frequency-Adaptive On-line Training for Fast and Accurate Natural Language Processing
	Sun, Xu ; Li, Wenjie ; Wang, Houfeng ; Lu, Qin
刊名	computational linguistics
	2014
关键词	WORD SEGMENTATION
DOI	10.1162/COLI_a_00193
英文摘要	Training speed and accuracy are two major concerns of large-scale natural language processing systems. Typically, we need to make a tradeoff between speed and accuracy. It is trivial to improve the training speed via sacrificing accuracy or to improve the accuracy via sacrificing speed. Nevertheless, it is nontrivial to improve the training speed and the accuracy at the same time, which is the target of this work. To reach this target, we present a new training method, feature-frequency-adaptive on-line training, for fast and accurate training of natural language processing systems. It is based on the core idea that higher frequency features should have a learning rate that decays faster. Theoretical analysis shows that the proposed method is convergent with a fast convergence rate. Experiments are conducted based on well-known benchmark tasks, including named entity recognition, word segmentation, phrase chunking, and sentiment analysis. These tasks consist of three structured classification tasks and one non-structured classification task, with binary features and real-valued features, respectively. Experimental results demonstrate that the proposed method is faster and at the same time more accurate than existing methods, achieving state-of-the-art scores on the tasks with different characteristics.; Computer Science, Artificial Intelligence; Computer Science, Interdisciplinary Applications; Linguistics; Language & Linguistics; A&HCI; SCI(E); SSCI; 0; ARTICLE; xusun@pku.edu.cn; cswjli@comp.polyu.edu.hk; wanghf@pku.edu.cn; csluqin@comp.polyu.edu.hk; 3; 563-586; 40
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/388305]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Sun, Xu,Li, Wenjie,Wang, Houfeng,et al. Feature-Frequency-Adaptive On-line Training for Fast and Accurate Natural Language Processing[J]. computational linguistics,2014.
APA	Sun, Xu,Li, Wenjie,Wang, Houfeng,&Lu, Qin.(2014).Feature-Frequency-Adaptive On-line Training for Fast and Accurate Natural Language Processing.computational linguistics.
MLA	Sun, Xu,et al."Feature-Frequency-Adaptive On-line Training for Fast and Accurate Natural Language Processing".computational linguistics (2014).