Truncation Sampling as Language Model Desmoothing

Abstract

Long samples of text from neural language models can be of poor quality. Truncation sampling algorithms–like top-p or top-k—address this by setting some words’ probabilities to zero at each step. This work investigates why these methods are important, and how to improve them. We propose thinking of a neural language model as a mixture of a true distribution and a smoothing distribution that avoids infinite perplexity. In this light, truncation algorithms aim to perform desmoothing, estimating a subset of the support of the true distribution. Finding a good subset is crucial: we show that top-p unnecessarily truncates high-probability words, for example causing it to truncate all words but Trump for a document that starts with Donald. We introduce eta-sampling, which truncates words below an entropy-dependent probability threshold. Compared to previous algorithms, our eta-sampling generates more plausible long documents according to humans, is better at breaking out of repetition, and behaves more reasonably on a battery of test distributions.