Towards Building an Open-Domain Dialogue System Incorporated with Internet Memes
This work addresses the problem of making online conversations more expressive and attractive for users by incorporating memes, though it is incremental as it builds on existing pre-trained models and focuses on specific tasks in a challenge setting.
The paper tackled the challenge of integrating Internet memes into open-domain dialogue systems by addressing text response modeling, meme retrieval, and meme emotion classification, and demonstrated effective incorporation on the MOD dataset.
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.