Hierarchical Hybrid Attention Networks for Chinese Conversation Topic Classification

	Hierarchical Hybrid Attention Networks for Chinese Conversation Topic Classification
	Zhou, Yujun; Li, Changliang; Xu, Bo; Xu, Jiaming; Cao, Jie; Xu, Bo
	2017
会议名称	the 24th International Conference On Neural Information Processing (ICONIP)
会议日期	November 14-18, 2017
会议地点	Guangzhou, China
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.
关键词	Hierarchical Attention Networks Chinese Conversation Topic Classification Recurrent Neural Networks
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41051
专题	复杂系统认知与决策实验室_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],2017.