Evaluation of Neural Network Language Models in Handwritten Chinese Text Recognition

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Evaluation of Neural Network Language Models in Handwritten Chinese Text Recognition
	Wu YC(吴一超); Yin F(殷飞); Liu CL(刘成林)
	2015
会议名称	2015 13th International Conference on Document Analysis and Recognition
会议日期	2015-8-23
会议地点	法国南锡
摘要	Handwritten Chinese text recognition based on over-segmentation and path search integrating contexts has been demonstrated successful, where language models play an important role. Recently, neural network language models (NNLMs) have shown superiority to back-off N-gram language models (BLMs) in handwriting recognition, but have not been studied in Chinese text recognition system. This paper investigates the effects of NNLMs in handwritten Chinese text recognition and compares the performance with BLMs. We trained characterlevel language models in 3-, 4- and 5- gram on large scale corpora and applied them in text line recognition system. Experimental results on the CASIA-HWDB database show that NNLM and BLM of the same order perform comparably, and the hybrid model by interpolating NNLM and BLM improves the recognition performance significantly.
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/19797
专题	多模态人工智能系统全国重点实验室_模式分析与学习
作者单位	Institute of Institute of Automation,Chinese Academy of Sciences
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wu YC,Yin F,Liu CL. Evaluation of Neural Network Language Models in Handwritten Chinese Text Recognition[C],2015.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
paper_078.pdf（1450KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载