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.
@article{arxiv.2005.01279,
title = {Improving Adversarial Text Generation by Modeling the Distant Future},
author = {Ruiyi Zhang and Changyou Chen and Zhe Gan and Wenlin Wang and Dinghan Shen and Guoyin Wang and Zheng Wen and Lawrence Carin},
journal= {arXiv preprint arXiv:2005.01279},
year = {2020}
}
Comments
ACL 2020. arXiv admin note: substantial text overlap with arXiv:1811.00696