资源分类
》 资源 》论文》Probabilistic Counting with Randomized Storage

Probabilistic Counting with Randomized Storage

2019-11-15 | |  86 |   60 |   0

Abstract Previous work by Talbot and Osborne [2007] explored the use of randomized storage mechanisms in language modeling. These structures trade a small amount of error for signifificant space savings, enabling the use of larger language models on relatively modest hardware. Going beyond space effificient count storage, here we present the Talbot Osborne Morris Bloom (TOMB) Counter, an extended model for performing space effificient counting over streams of fifinite length. Theoretical and experimental results are given, showing the promise of approximate counting over large vocabularies in the context of limited space

上一篇：Introspection and Adaptable Model Integration for Dialogue-based Question Answering

下一篇：A Translation-based Approach to Contingent Planning

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...