Dual Task Framework for Improving Persona-Grounded Dialogue Dataset

Minju Kim; Beong-woo Kwak; Youngwook Kim; Hong-in Lee; Seung-won Hwang; Jinyoung Yeo

doi:10.1609/aaai.v36i10.21338

Dual Task Framework for Improving Persona-Grounded Dialogue Dataset

@ AAAI 2022 || PDF

Authors

{Minju Kim, Beong-woo Kwak}, Youngwook Kim, Hong-in Lee, Seung-won Hwang, Jinyoung Yeo

Keywords

Persona grounded dialogue, Commonsense, Dual task, Bias in dataset

Abstract

This paper introduces a simple yet effective data-centric approach for the task of improving persona-conditioned dialogue agents. Prior model-centric approaches unquestioningly depend on the raw crowdsourced benchmark datasets such as Persona-Chat. In contrast, we aim to fix annotation artifacts in benchmarking, which is orthogonally applicable to any dialogue model. Specifically, we augment relevant personas to improve dialogue dataset/agent, by leveraging the primal-dual structure of the two tasks, predicting dialogue responses and personas based on each other. Experiments on Persona-Chat show that our approach outperforms pre-trained LMs by an 11.7 point gain in terms of accuracy.