NeurIPS 2020poster23 citations

ColdGANs: Taming Language GANs with Cautious Sampling Strategies

Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano

Abstract

Training regimes based on Maximum Likelihood Estimation (MLE) suffer from known limitations, often leading to poorly generated text sequences that lack of coherence, factualness, and are prone to repetitions. At the root of these limitations is the mismatch between training and inference, i.e. the so-called exposure bias. Another problem lies in considering only the reference text as correct, while in practice several alternative formulations could be as good.

BibTeX
@inproceedings{NEURIPS2020_db261d4f,
 author = {Scialom, Thomas and Dray, Paul-Alexis and Lamprier, Sylvain and Piwowarski, Benjamin and Staiano, Jacopo},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {18978--18989},
 publisher = {Curran Associates, Inc.},
 title = {ColdGANs: Taming Language GANs with Cautious Sampling Strategies},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/db261d4f615f0e982983be499e57ccda-Paper.pdf},
 volume = {33},
 year = {2020}
}
ColdGANs: Taming Language GANs with Cautious Sampling Strategies · NeurIPS 2020