QQ客服 官方微博 反馈留言

	Hierarchical Hybrid Attention Networks for Chinese Conversation Topic Classification
	Zhou, Yujun; Li, Changliang; Xu, Bo; Xu, Jiaming; Cao, Jie; Xu, Bo
	2017
会议日期	November 14-18, 2017
会议地点	Guangzhou, China
关键词	Hierarchical Attention Networks Chinese Conversation Topic Classification Recurrent Neural Networks
英文摘要	Topic classification is useful for applications such as forensics analysis and cyber-crime investigation. To improve the overall performance on the task of Chinese conversation topic classi?cation, we propose a hierarchical neural network with automatic semantic features selection, which is a hierarchical architecture that depicts the structure of conversations. The model firstly incorporates speaker information into the character- and word-level attentions and generates sentence representation, then uses attention-based BLSTM to construct the conversation representation. Experimental results on three datasets demonstrate that our model achieves better performance than multiple baselines. It indicates that the proposed architecture can capture the informative and salient features related to the meaning of a conversation for topic classification. And we release the dataset of this paper that can be obtained from https://github.com/njoe9/H-HANs.
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/41051]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者	Li, Changliang
推荐引用方式 GB/T 7714	Zhou, Yujun,Li, Changliang,Xu, Bo,et al. Hierarchical Hybrid Attention Networks for Chinese Conversation Topic Classification[C]. 见:. Guangzhou, China. November 14-18, 2017.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。