BriefGPT.xyz
Dec, 2020
开放域问答的高效内存基线
A Memory Efficient Baseline for Open Domain Question Answering
HTML
PDF
Gautier Izacard, Fabio Petroni, Lucas Hosseini, Nicola De Cao, Sebastian Riedel...
TL;DR
本文研究了基于密集表示的检索系统如何减少内存占用，并提出了三个方法：降维、量化和过滤。在TriviaQA和NaturalQuestions数据集上进行评估后，发现使用不到6GB的内存就能获得可以与竞品相媲美的系统。
Abstract
Recently, retrieval systems based on
dense representations
have led to important improvements in
open-domain question answering
, and related tasks. While very effective, this approach is also memory intensive, as
→