Distributed Deep Learning for Question Answering

被引：4

作者：

Feng, Minwei ^{[1
]}

Xiang, Bing ^{[1
]}

Zhou, Bowen ^{[1
]}

机构：

[1] IBM Watson, Yorktown Hts, NY 10598 USA

来源：

CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT | 2016年

关键词：

distributed training; deep learning; question answering;

D O I：

10.1145/2983323.2983377

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper is an empirical study of the distributed deep learning for question answering subtasks: answer selection and question classification. Comparison studies of SGD, MSGD, ADADELTA, ADAGRAD, ADAM/ADAMAX, RMSPROP, DOWNPOUR and EASGD/EAMSGD algorithms have been presented. Experimental results show that the distributed framework based on the message passing interface can accelerate the convergence speed at a sublinear scale. This paper demonstrates the importance of distributed training. For example, with 48 workers, a 24x speedup is achievable for the answer selection task and running time is decreased from 138.2 hours to 5.81 hours, which will increase the productivity significantly.

引用

页码：2413 / 2416

页数：4

共 50 条

[41] Improving Retrieval-Based Question Answering with Deep Inference Models
Pirtoaca, George-Sebastian
Rebedea, Traian
Ruseti, Stefan
2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
[42] Learning to rank for why-question answering
Verberne, Suzan
van Halteren, Hans
Theijssen, Daphne
Raaijmakers, Stephan
Boves, Lou
INFORMATION RETRIEVAL, 2011, 14 (02): : 107 - 132
[43] Multitask learning for neural generative question answering
Yanzhou Huang
Tao Zhong
Machine Vision and Applications, 2018, 29 : 1009 - 1017
[44] A Machine Learning Approach for Ranking in Question Answering
Amato, Alba
Coronato, Antonio
ADVANCES ON P2P, PARALLEL, GRID, CLOUD AND INTERNET COMPUTING (3PGCIC-2017), 2018, 13 : 89 - 98
[45] A Machine Learning Approach for Factoid Question Answering
Sal, David Dominguez
Surdeanu, Mihai
PROCESAMIENTO DEL LENGUAJE NATURAL, 2006, (37): : 131 - 136
[46] Multitask learning for neural generative question answering
Huang, Yanzhou
Zhong, Tao
MACHINE VISION AND APPLICATIONS, 2018, 29 (06) : 1009 - 1017
[47] A Novel Approach for Semantic Similarity Measurement for High Quality Answer Selection in Question Answering using Deep Learning Methods
Vekariya, Darshana V.
Limbasiya, Nivid R.
2020 6TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING AND COMMUNICATION SYSTEMS (ICACCS), 2020, : 518 - 522
[48] Enhanced Simple Question Answering with Contrastive Learning
Wang, Xin
Yang, Lan
He, Honglian
Fang, Yu
Zhan, Huayi
Zhang, Ji
KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, 2022, 13368 : 502 - 515
[49] Learning to rank for why-question answering
Suzan Verberne
Hans van Halteren
Daphne Theijssen
Stephan Raaijmakers
Lou Boves
Information Retrieval, 2011, 14 : 107 - 132
[50] Integrating Non-monotonic Logical Reasoning and Inductive Learning With Deep Learning for Explainable Visual Question Answering
Riley, Heather
Sridharan, Mohan
FRONTIERS IN ROBOTICS AND AI, 2019, 6

← 1 2 3 4 5 →