Topic-enhanced emotional conversation generation with attention mechanism

Topic-enhanced emotional conversation generation with attention mechanism
复制标题

利用注意力机制生成主题增强的情感对话

DOI:
10.1016/j.knosys.2018.09.006
复制
发表时间:
2019
期刊:
Knowledge-Based Systems (KBS, SCI二区, IF=5.101)
影响因子:
--
通讯作者:
Guangyou Zhou
Guangyou Zhou
中科院分区:
其他
文献类型:
--
作者:
Yehong Peng;Yizhen Fang;Zhiwen Xie;Guangyou Zhou

文献摘要

参考文献

被引文献

相似文献

情感对话的产生引起了学术界和产业界的广泛兴趣。然而,现有的情绪神经对话系统往往忽略了在产生反应时将话题和情绪结合起来的必要性,这可能会导致反应质量的下降。提出了一种话题增强型情感会话生成模型,该模型通过两种机制将情感因素和话题信息融入到会话系统中。首先,我们使用推特潜在狄利克雷分配(LDA)模型来获取输入序列的主题词作为额外的先验信息,以确保帖子和回复之间的内容一致性,以生成情感对话。其次,系统使用动态情感注意机制自适应地获取输入文本和额外主题的内容相关和情感信息。本研究的优势在于所提出的模型能够产生丰富的情感反应,其内容具有关联性和多样性。为了验证该方法的有效性,我们在大规模的微博回复对上进行了大量的实验。实验结果表明,我们的方法取得了很好的性能,甚至超过了现有的一些模型。
Emotional conversation generation has elicited a wide interest in both academia and industry. However, existing emotional neural conversation systems tend to ignore the necessity to combine topic and emotion in generating responses, possibly leading to a decline in the quality of responses. This paper proposes a topic-enhanced emotional conversation generation model that incorporates emotional factors and topic information into the conversation system, by using two mechanisms. First, we use a Twitter latent Dirichlet allocation (LDA) model to obtain topic words of the input sequences as extra prior information, ensuring the consistency of content between posts and responses for emotional conversation generation. Second, the system uses a dynamic emotional attention mechanism to adaptively acquire content-related and affective information of the input texts and extra topics. The advantage of this study lies in the fact that the presented model can generate abundant emotional responses, with the contents being related and diverse. To demonstrate the effectiveness of our method, we conduct extensive experiments on large-scale Weibo post–response pairs. Experimental results show that our method achieves good performance, even outperforming some existing models.
DOI: 10.1007/978-3-642-24600-5_37
发表时间: 2011-10
期刊: --
影响因子: --
作者:
M. Skowron;Stefan Rank;Mathias Theunis;J. Sienkiewicz
通讯作者: M. Skowron;Stefan Rank;Mathias Theunis;J. Sienkiewicz
DOI: 10.1007/978-3-319-73618-1_5
发表时间: 2017-11
期刊: --
影响因子: --
作者:
Yimeng Zhuang;Xianliang Wang;Han Zhang;Jinghui Xie;Xuan Zhu
通讯作者: Yimeng Zhuang;Xianliang Wang;Han Zhang;Jinghui Xie;Xuan Zhu
DOI: 10.1145/3077136.3080843
发表时间: 2017-08
期刊: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval
影响因子: --
作者:
Rui Yan;Dongyan Zhao;E. Weinan
通讯作者: Rui Yan;Dongyan Zhao;E. Weinan
DOI: --
发表时间: 2009-07
期刊: --
影响因子: --
作者:
M. Ptaszynski;Pawel Dybala;Wenhan Shi;Rafal Rzepka;K. Araki
通讯作者: M. Ptaszynski;Pawel Dybala;Wenhan Shi;Rafal Rzepka;K. Araki
DOI: --
发表时间: 2013-10
影响因子: --
作者:
Hao Wang;Zhengdong Lu;Hang Li;Enhong Chen
通讯作者: Hao Wang;Zhengdong Lu;Hang Li;Enhong Chen