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

[31] Deep Learning Powered Question-Answering Framework for Organizations Digital Transformation
Carvalho, Nuno Ramos
Barbosa, Luis Soares
PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON THEORY AND PRACTICE OF ELECTRONIC GOVERNANCE (ICEGOV2019), 2019, : 76 - 79
[32] Deep learning-based question answering system for intelligent humanoid robot
Widodo Budiharto
Vincent Andreas
Alexander Agung Santoso Gunawan
Journal of Big Data, 7
[33] Expert2Vec: Distributed Expert Representation Learning in Question Answering Community
Chen, Xiaocong
Huang, Chaoran
Zhang, Xiang
Wang, Xianzhi
Liu, Wei
Yao, Lina
ADVANCED DATA MINING AND APPLICATIONS, ADMA 2019, 2019, 11888 : 288 - 301
[34] A question answering system based on mineral exploration ontology generation: A deep learning methodology
Qiu, Qinjun
Tian, Miao
Ma, Kai
Tan, Yong Jian
Tao, Liufeng
Xie, Zhong
ORE GEOLOGY REVIEWS, 2023, 153
[35] Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering
Tay, Yi
Luu Anh Tuan
Hui, Siu Cheung
WSDM'18: PROCEEDINGS OF THE ELEVENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2018, : 583 - 591
[36] Research and Implementation of Railway Technical Specification Question Answering System Based on Deep Learning
Hu, Zhaohua
PROCEEDINGS OF 2020 IEEE 5TH INFORMATION TECHNOLOGY AND MECHATRONICS ENGINEERING CONFERENCE (ITOEC 2020), 2020, : 5 - 9
[37] Knowledge Graph - Deep Learning: A Case Study in Question Answering in Aviation Safety Domain
Agarwal, Ankush
Gite, Raj
Laddha, Shreya
Bhattacharyya, Pushpak
Kar, Satyanarayan
Ekbal, Asif
Thind, Prabhjit
Zele, Rajesh
Shankar, Ravi
LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2022, : 6260 - 6270
[38] Developing an Open Domain Arabic Question Answering System Using a Deep Learning Technique
Alkhurayyif, Yazeed
Sait, Abdul Rahaman Wahab
IEEE ACCESS, 2023, 11 : 69131 - 69143
[39] Developing a Vietnamese Tourism Question Answering System Using Knowledge Graph and Deep Learning
Phuc Do
Phan, Truong H., V
Gupta, Brij B.
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2021, 20 (05)
[40] Adapting and evaluating a deep learning language model for clinical why-question answering
Wen, Andrew
Elwazir, Mohamed Y.
Moon, Sungrim
Fan, Jungwei
JAMIA OPEN, 2020, 3 (01) : 16 - 20

← 1 2 3 4 5 →