SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.02102 · ACL · 2021

Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints

Sebastian Riedel, Pasquale Minervini, Pontus Stenetorp, Yuxiang Wu

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

Adaptive Computation (AC) has been shown to be effective in improving the efficiency of Open-Domain Question Answering (ODQA) systems. However, current AC approaches require tuning of all model parameters, and training state-of-the-art ODQA models requires significant computational resources that may not be available for most researchers. We propose Adaptive Passage Encoder, an AC method that can be applied to an existing ODQA model and can be trained efficiently on a single GPU. It keeps the parameters of the base ODQA model fixed, but it overrides the default layer-by-layer computation of the encoder with an AC policy that is trained to optimise the computational efficiency of the model. Our experimental results show that our method improves upon a state-of-theart model on two datasets, and is also more accurate than previous AC methods due to the stronger base ODQA model. All source code and datasets are available at https:// github.com/uclnlp/APE.

For agents

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

get_harvested_code_for_paper("2107.02102")
get_code_for_paper("2107.02102")
have("2107.02102")

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

curl https://syntology.ai/api/ran/2107.02102.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.02102.svg)](https://syntology.ai/paper/2107.02102)

Connect an agent — have() is free.