Dynamic Evaluation of Neural Sequence Models

Ben Krause, Emmanuel Kahembwe, Iain Murray, Steve Renals

Abstract: We present methodology for using dynamic evaluation to improve neural sequence models. Models are adapted to recent history via a gradient descent based mechanism, causing them to assign higher probabilities to re-occurring sequential patterns. Dynamic evaluation outperforms existing adaptation approaches in our comparisons. Dynamic evaluation improves the state-of-the-art word-level perplexities on the Penn Treebank and WikiText-2 datasets to 51.1 and 44.3 respectively, and the state-of-the-art character-level cross-entropies on the text8 and Hutter Prize datasets to 1.19 bits/char and 1.08 bits/char respectively.

TL;DR: Paper presents dynamic evaluation methodology for adaptive sequence modelling

Keywords: sequence modelling, language, recurrent neural networks, adaptation

Community Implementations: [ 7 code implementations](https://www.catalyzex.com/paper/arxiv:1709.07432/code)