Research Article
Learning Parameter Analysis for Machine Reading Comprehension
6 downloads
@INPROCEEDINGS{10.1007/978-3-030-72792-5_39, author={Xuekui Li and Lei Chen and Yi Shi and Ping Cui}, title={Learning Parameter Analysis for Machine Reading Comprehension}, proceedings={Simulation Tools and Techniques. 12th EAI International Conference, SIMUtools 2020, Guiyang, China, August 28-29, 2020, Proceedings, Part I}, proceedings_a={SIMUTOOLS}, year={2021}, month={4}, keywords={Machine reading comprehension BiDAF Bleu Rouge-I Parameter analysis Deep learning}, doi={10.1007/978-3-030-72792-5_39} }- Xuekui Li
Lei Chen
Yi Shi
Ping Cui
Year: 2021
Learning Parameter Analysis for Machine Reading Comprehension
SIMUTOOLS
Springer
DOI: 10.1007/978-3-030-72792-5_39
Abstract
Machine reading comprehension is a classic issue artificial intelligence. It is a key technology in the next generation search engine and intelligent interactive service. The traditional methods usually work in a small scale of data sets. The traditional system cannot meet the emerging demand. Deep learning and cloud computation have ability to deal with the large scale data sets. In real scene, the parameters affect the performance of machine reading comprehension task. In this paper, we analyze how the parameters of deep neural network affect the machine reading comprehension. The experiment results show that the performance is only sensitive to a few parameters which should be key point for engineers.
Copyright © 2020–2025 ICST
