# Overprotective Training Environments Fall Short at Testing Time: Let Models Contribute to Their Own Training

arXiv: https://arxiv.org/abs/2103.11145 · HTML: https://mlsanity.com/paper/2103.11145/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 20 Mar 2021.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Visual Dialog](https://mlsanity.com/paper/1611.08669/) (2016)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [GuessWhat?! Visual object discovery through multi-modal dialogue](https://mlsanity.com/paper/1611.08481/) (2016)
- [Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.06585/) (2017)
- [Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation](https://mlsanity.com/paper/1701.08251/) (2017)
- [Improving Generative Visual Dialog by Answering Diverse Questions](https://mlsanity.com/paper/1909.10470/) (2019)
- [Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat](https://mlsanity.com/paper/1809.03408/) (2018)

## Abstract (arXiv)

Despite important progress, conversational systems often generate dialogues that sound unnatural to humans. We conjecture that the reason lies in their different training and testing conditions: agents are trained in a controlled "lab" setting but tested in the "wild". During training, they learn to generate an utterance given the human dialogue history. On the other hand, during testing, they must interact with each other, and hence deal with noisy data. We propose to fill this gap by training the model with mixed batches containing both samples of human and machine-generated dialogues. We assess the validity of the proposed method on GuessWhat?!, a visual referential game.