English

Location-Aware Visual Question Generation with Lightweight Models

Computation and Language 2023-10-24 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2310.15129,
  title  = {Location-Aware Visual Question Generation with Lightweight Models},
  author = {Nicholas Collin Suwono and Justin Chih-Yao Chen and Tun Min Hung and Ting-Hao Kenneth Huang and I-Bin Liao and Yung-Hui Li and Lun-Wei Ku and Shao-Hua Sun},
  journal= {arXiv preprint arXiv:2310.15129},
  year   = {2023}
}

Comments

EMNLP 2023

R2 v1 2026-06-28T12:59:16.498Z