Knowledge fragment enrichment using domain knowledge base

Jing Zhang; Honglei Zhuang; Yanglei Song; Jiawei Han; Yutao Zhang; Jie Tang; Juanzi Li

doi:10.1007/978-981-10-2993-6_24

Knowledge fragment enrichment using domain knowledge base

Jing Zhang, Honglei Zhuang, Yanglei Song, Jiawei Han, Yutao Zhang, Jie Tang, Juanzi Li

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Knowledge fragment enrichment aims to complete user input concept fragment by augmenting each concept with rich domain information. This is a widely studied problem in cognitive science, but has not been intensively investigated in computer science. In this paper, we formally define the problem of knowledge fragment enrichment in domain knowledge base and develop a probabilistic graphical model to tackle the problem. The proposed model is able to model the dependencies among concepts in the input knowledge fragment and also capture the probabilistic relationship between concepts and domain entities. We empirically evaluate the proposed model on two different genres of datasets: PubMed and NSFC. On both datasets, the proposed model significantly improves the accuracy of label prediction task by up to 3–9% (in terms of MAP) compared with several alternative enrichment methods.

Original language	English (US)
Title of host publication	Social Media Processing - 5th National Conference, SMP 2016, Proceedings
Editors	Hongfei Lin, Yuming Li, Guoxiong Xiang, Mingwen Wang
Publisher	Springer
Pages	274-286
Number of pages	13
ISBN (Print)	9789811029929
DOIs	https://doi.org/10.1007/978-981-10-2993-6_24
State	Published - 2016
Event	5th National Conference on Social Media Processing, SMP 2016 - Nanchang, China Duration: Oct 29 2016 → Oct 30 2016

Publication series

Name	Communications in Computer and Information Science
Volume	669
ISSN (Print)	1865-0929

Other

Other	5th National Conference on Social Media Processing, SMP 2016
Country/Territory	China
City	Nanchang
Period	10/29/16 → 10/30/16

Keywords

Heterogeneous information networks
Hierarchical topic modeling
Semi-supervised labeling

ASJC Scopus subject areas

Computer Science(all)
Mathematics(all)

Online availability

10.1007/978-981-10-2993-6_24

Library availability

Discover UIUC Full Text

Cite this

Zhang, J., Zhuang, H., Song, Y., Han, J., Zhang, Y., Tang, J., & Li, J. (2016). Knowledge fragment enrichment using domain knowledge base. In H. Lin, Y. Li, G. Xiang, & M. Wang (Eds.), Social Media Processing - 5th National Conference, SMP 2016, Proceedings (pp. 274-286). (Communications in Computer and Information Science; Vol. 669). Springer. https://doi.org/10.1007/978-981-10-2993-6_24

Knowledge fragment enrichment using domain knowledge base. / Zhang, Jing; Zhuang, Honglei; Song, Yanglei et al.

Social Media Processing - 5th National Conference, SMP 2016, Proceedings. ed. / Hongfei Lin; Yuming Li; Guoxiong Xiang; Mingwen Wang. Springer, 2016. p. 274-286 (Communications in Computer and Information Science; Vol. 669).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhang, J, Zhuang, H, Song, Y, Han, J, Zhang, Y, Tang, J & Li, J 2016, Knowledge fragment enrichment using domain knowledge base. in H Lin, Y Li, G Xiang & M Wang (eds), Social Media Processing - 5th National Conference, SMP 2016, Proceedings. Communications in Computer and Information Science, vol. 669, Springer, pp. 274-286, 5th National Conference on Social Media Processing, SMP 2016, Nanchang, China, 10/29/16. https://doi.org/10.1007/978-981-10-2993-6_24

@inproceedings{cbbf3da1907443b2881da562d6b26f93,

title = "Knowledge fragment enrichment using domain knowledge base",

abstract = "Knowledge fragment enrichment aims to complete user input concept fragment by augmenting each concept with rich domain information. This is a widely studied problem in cognitive science, but has not been intensively investigated in computer science. In this paper, we formally define the problem of knowledge fragment enrichment in domain knowledge base and develop a probabilistic graphical model to tackle the problem. The proposed model is able to model the dependencies among concepts in the input knowledge fragment and also capture the probabilistic relationship between concepts and domain entities. We empirically evaluate the proposed model on two different genres of datasets: PubMed and NSFC. On both datasets, the proposed model significantly improves the accuracy of label prediction task by up to 3–9% (in terms of MAP) compared with several alternative enrichment methods.",

keywords = "Heterogeneous information networks, Hierarchical topic modeling, Semi-supervised labeling",

author = "Jing Zhang and Honglei Zhuang and Yanglei Song and Jiawei Han and Yutao Zhang and Jie Tang and Juanzi Li",

year = "2016",

doi = "10.1007/978-981-10-2993-6_24",

language = "English (US)",

isbn = "9789811029929",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "274--286",

editor = "Hongfei Lin and Yuming Li and Guoxiong Xiang and Mingwen Wang",

booktitle = "Social Media Processing - 5th National Conference, SMP 2016, Proceedings",

address = "Germany",

note = "5th National Conference on Social Media Processing, SMP 2016 ; Conference date: 29-10-2016 Through 30-10-2016",

}

TY - GEN

T1 - Knowledge fragment enrichment using domain knowledge base

AU - Zhang, Jing

AU - Zhuang, Honglei

AU - Song, Yanglei

AU - Han, Jiawei

AU - Zhang, Yutao

AU - Tang, Jie

AU - Li, Juanzi

PY - 2016

Y1 - 2016

N2 - Knowledge fragment enrichment aims to complete user input concept fragment by augmenting each concept with rich domain information. This is a widely studied problem in cognitive science, but has not been intensively investigated in computer science. In this paper, we formally define the problem of knowledge fragment enrichment in domain knowledge base and develop a probabilistic graphical model to tackle the problem. The proposed model is able to model the dependencies among concepts in the input knowledge fragment and also capture the probabilistic relationship between concepts and domain entities. We empirically evaluate the proposed model on two different genres of datasets: PubMed and NSFC. On both datasets, the proposed model significantly improves the accuracy of label prediction task by up to 3–9% (in terms of MAP) compared with several alternative enrichment methods.

AB - Knowledge fragment enrichment aims to complete user input concept fragment by augmenting each concept with rich domain information. This is a widely studied problem in cognitive science, but has not been intensively investigated in computer science. In this paper, we formally define the problem of knowledge fragment enrichment in domain knowledge base and develop a probabilistic graphical model to tackle the problem. The proposed model is able to model the dependencies among concepts in the input knowledge fragment and also capture the probabilistic relationship between concepts and domain entities. We empirically evaluate the proposed model on two different genres of datasets: PubMed and NSFC. On both datasets, the proposed model significantly improves the accuracy of label prediction task by up to 3–9% (in terms of MAP) compared with several alternative enrichment methods.

KW - Heterogeneous information networks

KW - Hierarchical topic modeling

KW - Semi-supervised labeling

UR - http://www.scopus.com/inward/record.url?scp=84994494235&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994494235&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-2993-6_24

DO - 10.1007/978-981-10-2993-6_24

M3 - Conference contribution

AN - SCOPUS:84994494235

SN - 9789811029929

T3 - Communications in Computer and Information Science

SP - 274

EP - 286

BT - Social Media Processing - 5th National Conference, SMP 2016, Proceedings

A2 - Lin, Hongfei

A2 - Li, Yuming

A2 - Xiang, Guoxiong

A2 - Wang, Mingwen

PB - Springer

T2 - 5th National Conference on Social Media Processing, SMP 2016

Y2 - 29 October 2016 through 30 October 2016

ER -

Knowledge fragment enrichment using domain knowledge base

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this