Skip to main content

Improving adversarial text generation by modeling the distant future

Publication ,  Conference
Zhang, R; Chen, C; Gan, Z; Wang, W; Shen, D; Wang, G; Wen, Z; Carin, L
Published in: Proceedings of the Annual Meeting of the Association for Computational Linguistics
January 1, 2020

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.

Duke Scholars

Published In

Proceedings of the Annual Meeting of the Association for Computational Linguistics

ISSN

0736-587X

Publication Date

January 1, 2020

Start / End Page

2516 / 2531
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhang, R., Chen, C., Gan, Z., Wang, W., Shen, D., Wang, G., … Carin, L. (2020). Improving adversarial text generation by modeling the distant future. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (pp. 2516–2531).
Zhang, R., C. Chen, Z. Gan, W. Wang, D. Shen, G. Wang, Z. Wen, and L. Carin. “Improving adversarial text generation by modeling the distant future.” In Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2516–31, 2020.
Zhang R, Chen C, Gan Z, Wang W, Shen D, Wang G, et al. Improving adversarial text generation by modeling the distant future. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics. 2020. p. 2516–31.
Zhang, R., et al. “Improving adversarial text generation by modeling the distant future.” Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2020, pp. 2516–31.
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. 2020. p. 2516–2531.

Published In

Proceedings of the Annual Meeting of the Association for Computational Linguistics

ISSN

0736-587X

Publication Date

January 1, 2020

Start / End Page

2516 / 2531