MojiTalk: Generating Emotional Responses at Scale

Abstract

Generating emotional language is a key step towards building empathetic natural language processing agents. However, a major challenge for this line of research is the lack of large-scale labeled training data, and previous studies are limited to only small sets of human annotated sentiment labels. Additionally, explicitly controlling the emotion and sentiment of generated text is also difficult. In this paper, we take a more radical approach: we exploit the idea of leveraging Twitter data that are naturally labeled with emojis. More specifically, we collect a large corpus of Twitter conversations that include emojis in the response, and assume the emojis convey the underlying emotions of the sentence. We then introduce a reinforced conditional variational encoder approach to train a deep generative model on these conversations, which allows us to use emojis to control the emotion of the generated text. Experimentally, we show in our quantitative and qualitative analyses that the proposed models can successfully generate high-quality abstractive conversation responses in accordance with designated emotions.

References in corpus (8)

• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• Deep Reinforcement Learning for Dialogue Generation
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Toward Controlled Generation of Text
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
• Neural Emoji Recommendation in Dialogue Systems

Cited by in corpus (6)

• EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems
• Target Guided Emotion Aware Chat Machine
• Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
• A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph
• Domain-Constrained Advertising Keyword Generation
• Memory-Augmented Recurrent Networks for Dialogue Coherence