# Improving Adversarial Text Generation by Modeling the Distant Future

arXiv: https://arxiv.org/abs/2005.01279 · HTML: https://mlsanity.com/paper/2005.01279/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2020.

## Built on by (most cited first, 1 of 1)

- [Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation](https://mlsanity.com/paper/2106.06751/) (2021)

## Abstract (arXiv)

Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words with similar semantics is challenging, and hand-crafted linguistic rules are difficult to apply. We consider a text planning scheme and present a model-based imitation-learning approach to alleviate the aforementioned issues. Specifically, we propose a novel guider network to focus on the generative process over a longer horizon, which can assist next-word prediction and provide intermediate rewards for generator optimization. Extensive experiments demonstrate that the proposed method leads to improved performance.