MoEL: Mixture of Empathetic Listeners (EMNLP 2019)

- 7 mins

Abstract

1. Introduction

table1

figure1

3. Mixture of Empathetic Listeners

3.1. Embedding

figure2

3.2. Emtion Tracker

3.3. Emotion Aware Listeners

3.4. Meta Listener

Experiment

4.1. Dataset

4.2. Training

4.3. Baseline

4.4. Hyperparameter

4.5. Evaluation Metrics

5. Results

figure3

table2

6. Analysis

table4

figure4

7. Conclusion & Future Work

In this paper, we propose a novel way to generate empathetic dialogue responses by using Mixture of Empathetic Listeners (MoEL). Differently from previous works, our model understand the user feelings and responds accordingly by learning specific listeners for each emotion. We benchmark our model in empathetic-dialogues dataset (Rashkin et al., 2018), which is a multiturn open-domain conversation corpus grounded on emotional situations. Our experimental results show that MoEL is able to achieve competitive performance in the task with the advantage of being more interpretable than other conventional models. Finally, we show that our model is able to automatically select the correct emotional decoder and effectively generate an empathetic response. One of the possible extensions of this work would be incorporating it with Persona (Zhang et al., 2018a) and task-oriented dialogue systems (Gao et al., 2018; Madotto et al., 2018; Wu et al., 2019, 2017, 2018a; Reddy et al., 2018; Raghu et al., 2019). Having a persona would allow the system to have more consistent and personalized responses, and combining open-domain conversations with task-oriented dialogue systems would equip the system with more engaging conversational capabilities, hence resulting in a more versatile dialogue system.

Joohong Lee

Joohong Lee

Machine Learning Researcher

rss facebook twitter github youtube mail spotify instagram linkedin google pinterest medium