Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning

09/28/2020
by   Haochen Liu, et al.
7

Dialogue systems play an increasingly important role in various aspects of our daily life. It is evident from recent research that dialogue systems trained on human conversation data are biased. In particular, they can produce responses that reflect people's gender prejudice. Many debiasing methods have been developed for various natural language processing tasks, such as word embedding. However, they are not directly applicable to dialogue systems because they are likely to force dialogue models to generate similar responses for different genders. This greatly degrades the diversity of the generated responses and immensely hurts the performance of the dialogue models. In this paper, we propose a novel adversarial learning framework Debiased-Chat to train dialogue models free from gender bias while keeping their performance. Extensive experiments on two real-world conversation datasets show that our framework significantly reduces gender bias in dialogue models while maintaining the response quality.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/23/2019

DAL: Dual Adversarial Learning for Dialogue Generation

In open-domain dialogue systems, generative approaches have attracted mu...
11/10/2019

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Models often easily learn biases present in the training data, and their...
04/18/2021

Revealing Persona Biases in Dialogue Systems

Dialogue systems in the form of chatbots and personal assistants are bei...
04/30/2020

EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble Model on Short-Text Conversation

Generating qualitative responses has always been a challenge for human-c...
10/05/2020

Regularizing Dialogue Generation by Imitating Implicit Scenarios

Human dialogues are scenario-based and appropriate responses generally r...
09/07/2021

Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models

All AI models are susceptible to learning biases in data that they are t...
11/28/2017

End-to-end Adversarial Learning for Generative Conversational Agents

This paper presents a new adversarial learning method for generative con...