# Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards

arXiv: https://arxiv.org/abs/1711.07614 · HTML: https://mlsanity.com/paper/1711.07614/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2017.

## Built on by (most cited first, 7 of 7)

- [Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation](https://mlsanity.com/paper/2105.11541/) (2021)
- [Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue](https://mlsanity.com/paper/2106.15550/) (2021)
- [Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot](https://mlsanity.com/paper/2111.11099/) (2021)
- [Saying the Unseen: Video Descriptions via Dialog Agents](https://mlsanity.com/paper/2106.14069/) (2021)
- [Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser](https://mlsanity.com/paper/2109.02297/) (2021)
- [Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene](https://mlsanity.com/paper/2203.08362/) (2022)
- [Adversarial and Safely Scaled Question Generation](https://mlsanity.com/paper/2210.09467/) (2022)

## Abstract (arXiv)

Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge. Towards this end, we propose a Deep Reinforcement Learning framework based on three new intermediate rewards, namely goal-achieved, progressive and informativeness that encourage the generation of succinct questions, which in turn uncover valuable information towards the overall goal. By directly optimizing for questions that work quickly towards fulfilling the overall goal, we avoid the tendency of existing methods to generate long series of insane queries that add little value. We evaluate our model on the GuessWhat?! dataset and show that the resulting questions can help a standard Guesser identify a specific object in an image at a much higher success rate.