Location-Aware Visual Question Generation with Lightweight Models
This work addresses a domain-specific problem for applications in mobile or edge devices, but it is incremental as it builds on existing visual question generation methods with a location-aware twist.
The authors tackled the problem of generating engaging questions from location-aware visual data by introducing the LocaVQG task and a lightweight model, which outperformed baselines in human and automatic evaluations like BERTScore and ROUGE-2.
This work introduces a novel task, location-aware visual question generation (LocaVQG), which aims to generate engaging questions from data relevant to a particular geographical location. Specifically, we represent such location-aware information with surrounding images and a GPS coordinate. To tackle this task, we present a dataset generation pipeline that leverages GPT-4 to produce diverse and sophisticated questions. Then, we aim to learn a lightweight model that can address the LocaVQG task and fit on an edge device, such as a mobile phone. To this end, we propose a method which can reliably generate engaging questions from location-aware information. Our proposed method outperforms baselines regarding human evaluation (e.g., engagement, grounding, coherence) and automatic evaluation metrics (e.g., BERTScore, ROUGE-2). Moreover, we conduct extensive ablation studies to justify our proposed techniques for both generating the dataset and solving the task.