Publications [#369874] of Lawrence Carin

Papers Published

1. Zhang, R; Chen, C; Gan, Z; Wang, W; Shen, D; Wang, G; Wen, Z; Carin, L, Improving adversarial text generation by modeling the distant future, Proceedings of the Annual Meeting of the Association for Computational Linguistics (January, 2020), pp. 2516-2531, ISBN 9781952148255
   (last updated on 2024/12/31)

   Abstract:
   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.