CORC  > 北京大学  > 信息科学技术学院
A Tensor Neural Network with Layerwise Pretraining: Towards Effective Answer Retrieval
Bao, Xin-Qi ; Wu, Yun-Fang
刊名JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
2016
关键词artificial intelligence language parsing and understanding machine learning
DOI10.1007/s11390-016-1689-4
英文摘要In this paper we address the answer retrieval problem in community-based question answering. To fully capture the interactions between question-answer pairs, we propose an original tensor neural network to model the relevance between them. The question and candidate answers are separately embedded into different latent semantic spaces, and a 3-way tensor is then utilized to model the interactions between latent semantics. To initialize the network layers properly, we propose a novel algorithm called denoising tensor autoencoder (DTAE), and then implement a layerwise pretraining strategy using denoising autoencoders (DAE) on word embedding layers and DTAE on the tensor layer. The experimental results show that our tensor neural network outperforms various baselines with other competitive neural network methods, and our pretraining DTAE strategy improves the system's performance and robustness.; National High Technology Research and Development 863 Program of China [2015AA015403]; National Natural Science Foundation of China [61371129, 61572245]; Key Program of Social Science Foundation of China [12ZD227]; SCI(E); 中国科技核心期刊(ISTIC); 中国科学引文数据库(CSCD); ARTICLE; yikusitian1990@163.com; wuyf@pku.edu.cn; 6; 1151-1160; 31
语种英语
内容类型期刊论文
源URL[http://ir.pku.edu.cn/handle/20.500.11897/458618]  
专题信息科学技术学院
推荐引用方式
GB/T 7714
Bao, Xin-Qi,Wu, Yun-Fang. A Tensor Neural Network with Layerwise Pretraining: Towards Effective Answer Retrieval[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2016.
APA Bao, Xin-Qi,&Wu, Yun-Fang.(2016).A Tensor Neural Network with Layerwise Pretraining: Towards Effective Answer Retrieval.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY.
MLA Bao, Xin-Qi,et al."A Tensor Neural Network with Layerwise Pretraining: Towards Effective Answer Retrieval".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY (2016).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace