CBNU at TREC 2018 Incident Streams Track

Won Gyu Choi; Seung Hyeon Jo; Kyung Soon Lee

CBNU at TREC 2018 Incident Streams Track

Won Gyu Choi
, Seung Hyeon Jo
, Kyung Soon Lee

Jeonbuk National University

Research output: Conference(x) › Paper › peer-review

10 Scopus citations

Abstract

This paper describes the participation of the CBNU team at the TREC Incident Streams Track 2018. For tweet representation, crisis-related terms are represented as conceptual entities. For tweet classification, we have compared support vector machines and our deep learning model which combines class activation mapping with one-shot learning in convolutional neural networks.

Original language	English
State	Published - 2018
Event	27th Text REtrieval Conference, TREC 2018 - Gaithersburg, United States Duration: 2018.11.14 → 2018.11.16

Conference

Conference	27th Text REtrieval Conference, TREC 2018
Country/Territory	United States
City	Gaithersburg
Period	18.11.14 → 18.11.16

Keywords

Class activation mapping
Conceptual representation
Convolutional neural networks
Incident Streams
One-shot learning

Quacquarelli Symonds(QS) Subject Topics

Linguistics
Computer Science & Information Systems
Data Science

Cite this

@conference{86f2674161e94828a7177ab79b6fac65,

title = "CBNU at TREC 2018 Incident Streams Track",

abstract = "This paper describes the participation of the CBNU team at the TREC Incident Streams Track 2018. For tweet representation, crisis-related terms are represented as conceptual entities. For tweet classification, we have compared support vector machines and our deep learning model which combines class activation mapping with one-shot learning in convolutional neural networks.",

keywords = "Class activation mapping, Conceptual representation, Convolutional neural networks, Incident Streams, One-shot learning",

author = "Choi, \{Won Gyu\} and Jo, \{Seung Hyeon\} and Lee, \{Kyung Soon\}",

note = "Publisher Copyright: {\textcopyright} 2018 Copyright held by the owner/author(s).; 27th Text REtrieval Conference, TREC 2018 ; Conference date: 14-11-2018 Through 16-11-2018",

year = "2018",

language = "English",

}

TY - CONF

T1 - CBNU at TREC 2018 Incident Streams Track

AU - Choi, Won Gyu

AU - Jo, Seung Hyeon

AU - Lee, Kyung Soon

PY - 2018

Y1 - 2018

N2 - This paper describes the participation of the CBNU team at the TREC Incident Streams Track 2018. For tweet representation, crisis-related terms are represented as conceptual entities. For tweet classification, we have compared support vector machines and our deep learning model which combines class activation mapping with one-shot learning in convolutional neural networks.

AB - This paper describes the participation of the CBNU team at the TREC Incident Streams Track 2018. For tweet representation, crisis-related terms are represented as conceptual entities. For tweet classification, we have compared support vector machines and our deep learning model which combines class activation mapping with one-shot learning in convolutional neural networks.

KW - Class activation mapping

KW - Conceptual representation

KW - Convolutional neural networks

KW - Incident Streams

KW - One-shot learning

UR - https://www.scopus.com/pages/publications/85096420445

M3 - Paper

AN - SCOPUS:85096420445

T2 - 27th Text REtrieval Conference, TREC 2018

Y2 - 14 November 2018 through 16 November 2018

ER -

CBNU at TREC 2018 Incident Streams Track

Abstract

Conference

Keywords

Quacquarelli Symonds(QS) Subject Topics

Other files and links

Fingerprint

Cite this