MojiTalk: Generating Emotional Responses at Scale

11/11/2017
by   Xianda Zhou, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/14/2021

Generating Empathetic Responses with a Large Scale Dialog Dataset

The task of empathetic response generation aims at generating syntactica...
research
05/18/2021

Emotion Eliciting Machine: Emotion Eliciting Conversation Generation based on Dual Generator

Recent years have witnessed great progress on building emotional chatbot...
research
06/20/2019

HappyBot: Generating Empathetic Dialogue Responses by Improving User Experience Look-ahead

Recent neural conversation models that attempted to incorporate emotion ...
research
04/28/2013

Measuring Cultural Relativity of Emotional Valence and Arousal using Semantic Clustering and Twitter

Researchers since at least Darwin have debated whether and to what exten...
research
07/21/2017

A Sentiment-and-Semantics-Based Approach for Emotion Detection in Textual Conversations

Emotions are physiological states generated in humans in reaction to int...
research
06/25/2022

Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms

We describe our approach for the generative emotional vocal burst task (...
research
06/22/2021

Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication

The majority of existing methods for empathetic response generation rely...

Please sign up or login with your details

Forgot password? Click here to reset