1. Paper title

Improving Adversarial Text Generation by Modeling the Distant Future

2. link

https://www.aclweb.org/anthology/2020.acl-main.227.pdf

3. 摘要

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.

4. 要解决什么问题

自回归文本生成模型通常专注于局部流利性，但在长文本生成中可能出现不一致的语义。

5. 作者的主要贡献

一种引导网络：
关注于更长时间范围的生成，可以辅助下一词预测并为生成器优化提供中间奖励。
[?] 没看懂

6. 得到了什么结果

性能有提升

7. 关键字

长文本生成