arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08857cs.CL
收藏

用于情绪反应生成的修正正则化条件变分自编码器

Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generation

National University of Defense Technology(国防科技大学);University of Science and Technology of China(中国科学技术大学)

Yu-Ping Ruan, Zhen-Hua Ling

摘要:

本文提出了一种情感正则化条件变分自编码器模型(EZ-CVAE),用于生成情感会话响应。在传统的基于CVAE的情绪反应生成中,情绪标签只是作为先验、后验和解码器网络中的附加条件。考虑到情感风格与语言空间中的语义内容自然纠缠在一起,该模型通过引入额外的情感预测网络,利用情感标签来正则化CVAE潜在空间。在训练阶段,需要估计的潜变量同时预测输入响应的情感标签和标记序列。实验结果表明,与传统的CVAE模型相比,我们的B-CVAE模型可以学习到更多信息和结构化的潜在空间,并且输出比基线CVAE和序列到序列(Seq 2Seq)模型具有更好的内容和情感性能的响应。

英文摘要:

This paper presents an emotion-regularized conditional variational autoencoder (Emo-CVAE) model for generating emotional conversation responses. In conventional CVAE-based emotional response generation, emotion labels are simply used as additional conditions in prior, posterior and decoder networks. Considering that emotion styles are naturally entangled with semantic contents in the language space, the Emo-CVAE model utilizes emotion labels to regularize the CVAE latent space by introducing an extra emotion prediction network. In the training stage, the estimated latent variables are required to predict the emotion labels and token sequences of the input responses simultaneously. Experimental results show that our Emo-CVAE model can learn a more informative and structured latent space than a conventional CVAE model and output responses with better content and emotion performance than baseline CVAE and sequence-to-sequence (Seq2Seq) models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑