Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation

TL;DR

This paper introduces Image-Grounded Conversations (IGC), a new task involving generating natural conversations about shared images, supported by a new dataset, and demonstrates that combining visual and textual context improves conversation quality.

Contribution

The paper presents a novel IGC task, a new dataset of event-centric image conversations, and shows that multimodal context enhances conversational generation.

Findings

Visual and textual context combination improves conversation quality.

Humans outperform neural and retrieval models in IGC.

IGC bridges chit-chat and goal-directed dialogue models.

Abstract

The popularity of image sharing on social media and the engagement it creates between users reflects the important role that visual context plays in everyday conversations. We present a novel task, Image-Grounded Conversations (IGC), in which natural-sounding conversations are generated about a shared image. To benchmark progress, we introduce a new multiple-reference dataset of crowd-sourced, event-centric conversations on images. IGC falls on the continuum between chit-chat and goal-directed conversation models, where visual grounding constrains the topic of conversation to event-driven utterances. Experiments with models trained on social media data show that the combination of visual and textual context enhances the quality of generated conversational turns. In human evaluation, the gap between human performance and that of both neural and retrieval architectures suggests that multi-modal IGC presents an interesting challenge for dialogue research.