Multi-VQG: Generating Engaging Questions for Multiple Images

TL;DR

This paper introduces MVQG, a new dataset and models for generating engaging questions from multiple images, emphasizing story construction over single images to enhance question relevance and creativity.

Contribution

The paper presents a novel dataset and baseline models for multi-image question generation, highlighting the importance of story understanding in visual question generation.

Findings

Models can generate engaging questions by understanding image sequences.

Story-based question generation outperforms single-image approaches.

The dataset enables new research directions in visual storytelling and question generation.

Abstract

Generating engaging content has drawn much recent attention in the NLP community. Asking questions is a natural way to respond to photos and promote awareness. However, most answers to questions in traditional question-answering (QA) datasets are factoids, which reduce individuals' willingness to answer. Furthermore, traditional visual question generation (VQG) confines the source data for question generation to single images, resulting in a limited ability to comprehend time-series information of the underlying event. In this paper, we propose generating engaging questions from multiple images. We present MVQG, a new dataset, and establish a series of baselines, including both end-to-end and dual-stage architectures. Results show that building stories behind the image sequence enables models to generate engaging questions, which confirms our assumption that people typically construct a picture of the event in their minds before asking questions. These results open up an exciting challenge for visual-and-language models to implicitly construct a story behind a series of photos to allow for creativity and experience sharing and hence draw attention to downstream applications.