Improving Adversarial Text Generation By Modeling The Distant Future
Zhang Ruiyi, Chen Changyou, Gan Zhe, Wang Wenlin, Shen Dinghan, Wang Guoyin, Wen Zheng, Carin Lawrence. Arxiv 2020
[Paper]
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.
Similar Work