Integrated Triaging for Fast Reading Comprehension

Although according to several benchmarks automatic machine reading comprehension (MRC) systems have recently reached super-human performance, less attention has been paid to their computational efficiency. However, efficiency is of crucial importance for training and deployment in real world applica...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-09
Main Authors: Wu, Felix, Boyi Li, Wang, Lequn, Lao, Ni, Blitzer, John, Weinberger, Kilian Q
Format: Article
Language:English
Subjects:
Efficiency
Human performance
Reading comprehension
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Although according to several benchmarks automatic machine reading comprehension (MRC) systems have recently reached super-human performance, less attention has been paid to their computational efficiency. However, efficiency is of crucial importance for training and deployment in real world applications. This paper introduces Integrated Triaging, a framework that prunes almost all context in early layers of a network, leaving the remaining (deep) layers to scan only a tiny fraction of the full corpus. This pruning drastically increases the efficiency of MRC models and further prevents the later layers from overfitting to prevalent short paragraphs in the training set. Our framework is extremely flexible and naturally applicable to a wide variety of models. Our experiment on doc-SQuAD and TriviaQA tasks demonstrates its effectiveness in consistently improving both speed and quality of several diverse MRC models.
ISSN:2331-8422