Speeding Up Entmax

Abstract

Softmax is the de facto standard for normalizing logits in modern neural networks for language processing. 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. αentmax of Peters et al. ( 2019) solves this problem, but is unfortunately slower than softmax.In this paper, we propose an alternative to αentmax, which keeps its virtuous characteristics, but is as fast as optimized softmax and achieves on par or better performance in machine translation task.