Let's Talk! Striking Up Conversations via Conversational Visual Question Generation
This addresses the problem of initiating conversations for users of social media or conversational agents, though it appears incremental as it builds on existing vision-to-question models.
The paper tackles the problem of generating engaging conversation-starting questions from photo sets, where existing vision-to-question models produce tedious questions, and introduces a two-phase framework that first generates a visual story and then uses it to produce questions, with human evaluation showing it generates more response-provoking questions than baselines.
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.