IMAD: IMage-Augmented multi-modal Dialogue

TL;DR

This paper introduces IMAD, a novel multi-modal dialogue dataset combining images and dialogue, and proposes a baseline model that leverages visual context to enhance dialogue generation capabilities.

Contribution

The paper presents a new dataset, IMAD, constructed through a two-stage automatic process, and introduces a baseline model that effectively incorporates visual information into dialogue systems.

Findings

Baseline model outperforms text-only models.

IMAD dataset enables multi-modal dialogue research.

Effective image integration improves dialogue quality.

Abstract

Currently, dialogue systems have achieved high performance in processing text-based communication. However, they have not yet effectively incorporated visual information, which poses a significant challenge. Furthermore, existing models that incorporate images in dialogue generation focus on discussing the image itself. Our proposed approach presents a novel perspective on multi-modal dialogue systems, which interprets the image in the context of the dialogue. By doing so, we aim to expand the capabilities of current dialogue systems and transition them from single modality (text) to multi-modality. However, there is a lack of validated English datasets that contain both images and dialogue contexts for this task. Thus, we propose a two-stage approach to automatically construct a multi-modal dialogue dataset. In the first stage, we utilize text-to-image similarity and sentence similarity to identify which utterances could be replaced with an image. In the second stage, we replace those utterances by selecting a subset of relevant images and filtering them with a visual question answering model. We used this approach, along with additional labeling, to create the IMage Augmented multi-modal Dialogue dataset (IMAD), which can serve as a validated dataset for this task. Furthermore, we propose a baseline model trained on this dataset, which outperforms model trained on the same data without images and BlenderBot.