Generating Emotional Controllable Response Based on Multi-Task and Dual Attention Framework
Authors:
Open Access
- 12 June 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 93734-93741
Abstract
Building an empathic conversation agent in open-domain is a key step towards affective computing and intelligent interactions. However, most current methods either focus on the consistency of content or the controllability of emotion, and handling both factors are not yet properly solved. In this paper, we propose the multi-task and dual attentions (MTDA) framework for generating emotional response. The MTDA framework decomposes the input utterance into content layer and emotional layer, and then encodes and decodes them separately, which makes this end-to-end model more interpretable and controllable. A multi-task learning based encoder is employed in the MTDA framework, which can obtain the representation of the content and the emotion through unsupervised learning and supervised learning. A dual attention mechanism is adopted for decoding, which ensures that specific emotional responses are coherent with the content and the emotion of the input. We also combine the MTDA framework with state of the art generative models to train emotional generation systems. Extensive experiments show that our model can not only adapt to different target emotion goals, but also generate coherent and informative responses.Keywords
Funding Information
- Natural Science Foundation of Beijing Municipality (4174098)
- National Natural Science Foundation of China (61702047)
- National Natural Science Foundation of China (61703234)
- Fundamental Research Funds for the Central Universities (2017RC02)
This publication has 14 references indexed in Scilit:
- Affective Neural Response Generation2018
- Semi-supervised sequence tagging with bidirectional language models2017
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders2017
- Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm2017
- Attribute2Image: Conditional Image Generation from Visual Attributes2016
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation2016
- Generating Sentences from a Continuous Space2016
- Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval2015
- Neural Responding Machine for Short-Text Conversation2015
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014