Softmax is the de facto standard in modern neural networks for language processing when it comes to normalizing logits. However, by producing a dense probability distribution each token in the vocabulary has a nonzero chance of being selected at each generation step, leading to a variety of reported problems in text generation. α-entmax of Peters et al. (2019, arXiv:1905.05702) solves this problem, but is considerably slower than softmax. In this paper, we propose an alternative to α-entmax, which keeps its virtuous characteristics, but is as fast as optimized softmax and achieves on par or better performance in machine translation task.
@article{arxiv.2111.06832,
title = {Speeding Up Entmax},
author = {Maxat Tezekbayev and Vassilina Nikoulina and Matthias Gallé and Zhenisbek Assylbekov},
journal= {arXiv preprint arXiv:2111.06832},
year = {2022}
}