Progress and Tradeoffs in Neural Language Models
arXiv:1811.00942
Abstract
In recent years, we have witnessed a dramatic shift towards techniques driven by neural networks for a variety of NLP tasks. Undoubtedly, neural language models (NLMs) have reduced perplexity by impressive amounts. This progress, however, comes at a substantial cost in performance, in terms of inference latency and energy consumption, which is particularly of concern in deployments on mobile devices. This paper, which examines the quality-performance tradeoff of various language modeling techniques, represents to our knowledge the first to make this observation. We compare state-of-the-art NLMs with "classic" Kneser-Ney (KN) LMs in terms of energy usage, latency, perplexity, and prediction accuracy using two standard benchmarks. On a Raspberry Pi, we find that orders of increase in latency and energy usage correspond to less change in perplexity, while the difference is much less pronounced on a desktop.
arXiv comment5 pages, 4 figures
References in corpus (7)
- Effective Approaches to Attention-based Neural Machine Translation
- An Empirical Study of Smoothing Techniques for Language Modeling
- Pointer Sentinel Mixture Models
- Quasi-Recurrent Neural Networks
- Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
- An Analysis of Neural Language Modeling at Multiple Scales
- Fast Parametric Learning with Activation Memorization