Multimodal KB Harvesting for Emerging Spatial Entities

Jinyoung Yeo, Hyunsouk Cho, Jin Woo Park, Seungwon Hwang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

New entities are being created daily. Though the novelty of these entities naturally attracts mentions, due to lack of prior knowledge, it is more challenging to collect knowledge about such entities than pre-existing entities, whose KBs are comprehensively annotated through LBSNs and EBSNs. In this paper, we focus on knowledge harvesting for emerging spatial entities (ESEs), such as new businesses and venues, assuming we have only a list of ESE names. Existing techniques for knowledge base (KB) harvesting are primarily associated with information extraction from textual corpora. In contrast, we propose a multimodal method for event detection based on the complementary interaction of image, text, and user information between multi-source platforms, namely Flickr and Twitter. We empirically validate our harvesting approaches improve the quality of KB with enriched place and event knowledge.

Original languageEnglish
Article number7814228
Pages (from-to)1073-1086
Number of pages14
JournalIEEE Transactions on Knowledge and Data Engineering
Volume29
Issue number5
DOIs
Publication statusPublished - 2017 May 1

Fingerprint

Industry

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Yeo, Jinyoung ; Cho, Hyunsouk ; Park, Jin Woo ; Hwang, Seungwon. / Multimodal KB Harvesting for Emerging Spatial Entities. In: IEEE Transactions on Knowledge and Data Engineering. 2017 ; Vol. 29, No. 5. pp. 1073-1086.
@article{172c192d96694b91878ad0634ed67b14,
title = "Multimodal KB Harvesting for Emerging Spatial Entities",
abstract = "New entities are being created daily. Though the novelty of these entities naturally attracts mentions, due to lack of prior knowledge, it is more challenging to collect knowledge about such entities than pre-existing entities, whose KBs are comprehensively annotated through LBSNs and EBSNs. In this paper, we focus on knowledge harvesting for emerging spatial entities (ESEs), such as new businesses and venues, assuming we have only a list of ESE names. Existing techniques for knowledge base (KB) harvesting are primarily associated with information extraction from textual corpora. In contrast, we propose a multimodal method for event detection based on the complementary interaction of image, text, and user information between multi-source platforms, namely Flickr and Twitter. We empirically validate our harvesting approaches improve the quality of KB with enriched place and event knowledge.",
author = "Jinyoung Yeo and Hyunsouk Cho and Park, {Jin Woo} and Seungwon Hwang",
year = "2017",
month = "5",
day = "1",
doi = "10.1109/TKDE.2017.2651805",
language = "English",
volume = "29",
pages = "1073--1086",
journal = "IEEE Transactions on Knowledge and Data Engineering",
issn = "1041-4347",
publisher = "IEEE Computer Society",
number = "5",

}

Multimodal KB Harvesting for Emerging Spatial Entities. / Yeo, Jinyoung; Cho, Hyunsouk; Park, Jin Woo; Hwang, Seungwon.

In: IEEE Transactions on Knowledge and Data Engineering, Vol. 29, No. 5, 7814228, 01.05.2017, p. 1073-1086.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multimodal KB Harvesting for Emerging Spatial Entities

AU - Yeo, Jinyoung

AU - Cho, Hyunsouk

AU - Park, Jin Woo

AU - Hwang, Seungwon

PY - 2017/5/1

Y1 - 2017/5/1

N2 - New entities are being created daily. Though the novelty of these entities naturally attracts mentions, due to lack of prior knowledge, it is more challenging to collect knowledge about such entities than pre-existing entities, whose KBs are comprehensively annotated through LBSNs and EBSNs. In this paper, we focus on knowledge harvesting for emerging spatial entities (ESEs), such as new businesses and venues, assuming we have only a list of ESE names. Existing techniques for knowledge base (KB) harvesting are primarily associated with information extraction from textual corpora. In contrast, we propose a multimodal method for event detection based on the complementary interaction of image, text, and user information between multi-source platforms, namely Flickr and Twitter. We empirically validate our harvesting approaches improve the quality of KB with enriched place and event knowledge.

AB - New entities are being created daily. Though the novelty of these entities naturally attracts mentions, due to lack of prior knowledge, it is more challenging to collect knowledge about such entities than pre-existing entities, whose KBs are comprehensively annotated through LBSNs and EBSNs. In this paper, we focus on knowledge harvesting for emerging spatial entities (ESEs), such as new businesses and venues, assuming we have only a list of ESE names. Existing techniques for knowledge base (KB) harvesting are primarily associated with information extraction from textual corpora. In contrast, we propose a multimodal method for event detection based on the complementary interaction of image, text, and user information between multi-source platforms, namely Flickr and Twitter. We empirically validate our harvesting approaches improve the quality of KB with enriched place and event knowledge.

UR - http://www.scopus.com/inward/record.url?scp=85018523542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018523542&partnerID=8YFLogxK

U2 - 10.1109/TKDE.2017.2651805

DO - 10.1109/TKDE.2017.2651805

M3 - Article

AN - SCOPUS:85018523542

VL - 29

SP - 1073

EP - 1086

JO - IEEE Transactions on Knowledge and Data Engineering

JF - IEEE Transactions on Knowledge and Data Engineering

SN - 1041-4347

IS - 5

M1 - 7814228

ER -