CapWAP: Captioning with a Purpose

TL;DR

This paper introduces CapWAP, a new image captioning task focused on generating tailored captions that fulfill specific user information needs, optimized through reinforcement learning and evaluated using question-answering performance.

Contribution

It proposes a novel task, CapWAP, that uses user questions instead of reference captions for training and evaluation, enabling tailored and purpose-driven image captioning systems.

Findings

Purposeful captions improve QA accuracy on user questions.

Reinforcement learning effectively optimizes captions for specific information needs.

System outperforms generic captioning models in fulfilling targeted information requirements.

Abstract

The traditional image captioning task uses generic reference captions to provide textual information about images. Different user populations, however, will care about different visual aspects of images. In this paper, we propose a new task, Captioning with a Purpose (CapWAP). Our goal is to develop systems that can be tailored to be useful for the information needs of an intended population, rather than merely provide generic information about an image. In this task, we use question-answer (QA) pairs---a natural expression of information need---from users, instead of reference captions, for both training and post-inference evaluation. We show that it is possible to use reinforcement learning to directly optimize for the intended information need, by rewarding outputs that allow a question answering model to provide correct answers to sampled user questions. We convert several visual question answering datasets into CapWAP datasets, and demonstrate that under a variety of scenarios our purposeful captioning system learns to anticipate and fulfill specific information needs better than its generic counterparts, as measured by QA performance on user questions from unseen images, when using the caption alone as context.