Towards Building an Open-Domain Dialogue System Incorporated with Internet Memes

TL;DR

This paper introduces methods for integrating Internet memes into open-domain dialogue systems, enhancing expressiveness and attractiveness through response modeling, meme retrieval, and emotion classification, validated on the MOD dataset.

Contribution

We propose a comprehensive approach combining dialogue modeling, meme retrieval, and emotion flow modeling with auxiliary tasks to improve meme incorporation in dialogue systems.

Findings

Effective meme retrieval with good generalization.

Improved meme emotion classification performance.

Enhanced dialogue expressiveness with meme integration.

Abstract

In recent years, Internet memes have been widely used in online chatting. Compared with text-based communication, conversations become more expressive and attractive when Internet memes are incorporated. This paper presents our solutions for the Meme incorporated Open-domain Dialogue (MOD) Challenge of DSTC10, where three tasks are involved: text response modeling, meme retrieval, and meme emotion classification. Firstly, we leverage a large-scale pre-trained dialogue model for coherent and informative response generation. Secondly, based on interaction-based text-matching, our approach can retrieve appropriate memes with good generalization ability. Thirdly, we propose to model the emotion flow (EF) in conversations and introduce an auxiliary task of emotion description prediction (EDP) to boost the performance of meme emotion classification. Experimental results on the MOD dataset demonstrate that our methods can incorporate Internet memes into dialogue systems effectively.