SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.15156 · 2020

A Memory Efficient Baseline for Open Domain Question Answering

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 the dense vectors for the whole knowledge source need to be kept in memory. In this paper, we study how the memory footprint of dense retriever-reader systems can be reduced. We consider three strategies to reduce the index size: dimension reduction, vector quantization and passage filtering. We evaluate our approach on two question answering benchmarks: TriviaQA and NaturalQuestions, showing that it is possible to get competitive systems using less than 6Gb of memory.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2012.15156")
get_code_for_paper("2012.15156")
have("2012.15156")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2012.15156.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2012.15156.svg)](https://syntology.ai/paper/2012.15156)

Connect an agent — have() is free.