English

Let's Talk! Striking Up Conversations via Conversational Visual Question Generation

Artificial Intelligence 2022-05-20 v1 Computation and Language Computer Vision and Pattern Recognition

Abstract

An engaging and provocative question can open up a great conversation. In this work, we explore a novel scenario: a conversation agent views a set of the user's photos (for example, from social media platforms) and asks an engaging question to initiate a conversation with the user. The existing vision-to-question models mostly generate tedious and obvious questions, which might not be ideals conversation starters. This paper introduces a two-phase framework that first generates a visual story for the photo set and then uses the story to produce an interesting question. The human evaluation shows that our framework generates more response-provoking questions for starting conversations than other vision-to-question baselines.

Keywords

Cite

@article{arxiv.2205.09327,
  title  = {Let's Talk! Striking Up Conversations via Conversational Visual Question Generation},
  author = {Shih-Han Chan and Tsai-Lun Yang and Yun-Wei Chu and Chi-Yang Hsu and Ting-Hao Huang and Yu-Shian Chiu and Lun-Wei Ku},
  journal= {arXiv preprint arXiv:2205.09327},
  year   = {2022}
}

Comments

Accepted as a full talk paper on AAAI-DEEPDIAL'21

R2 v1 2026-06-24T11:21:51.639Z