Exploring concept graphs for biomedical literature mining

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Full-text publications in an electronic form become more prevalent than ever before. It is a difficult challenge to extract concepts from unstructured document collections data because different concepts and their relationships are buried in them and ample term variations make the challenge compound. Extracted concepts are useful instruments of managing and searching large document collections and play a pivotal role in indexing electronic documents and building digital libraries. In this paper we explore a biomedical concept extraction technique based on a ranking algorithm of concept graphs. The proposed technique comprises two major steps: the first step is to represent documents with graphs whose nodes and edges are created by Named Entity Recognition and UMLS Semantic Network. The second step is rank concepts with relative importance algorithms. We evaluate our technique with a set of biomedical full-texts and compare it to various different key-phrase extraction and graph ranking techniques. The experimental results show that our technique achieves the best performance over other compared algorithms. We further take a close look at the properties of the network to examine how concepts are related to each other and what concept plays a dominant role in the network. To this end, we build the network with 526 full-text articles published in PubMed Central and measure the significance of nodes by centrality.

Original languageEnglish
Title of host publication2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages103-110
Number of pages8
ISBN (Electronic)9781479973033
DOIs
Publication statusPublished - 2015 Jan 1
Event2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015 - Jeju, Korea, Republic of
Duration: 2015 Feb 92015 Feb 11

Other

Other2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015
CountryKorea, Republic of
CityJeju
Period15/2/915/2/11

Fingerprint

Digital libraries
Semantics

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Song, M. (2015). Exploring concept graphs for biomedical literature mining. In 2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015 (pp. 103-110). [7072818] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/35021BIGCOMP.2015.7072818
Song, Min. / Exploring concept graphs for biomedical literature mining. 2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 103-110
@inproceedings{91a2e4469cb04c648246f0d0167b0df9,
title = "Exploring concept graphs for biomedical literature mining",
abstract = "Full-text publications in an electronic form become more prevalent than ever before. It is a difficult challenge to extract concepts from unstructured document collections data because different concepts and their relationships are buried in them and ample term variations make the challenge compound. Extracted concepts are useful instruments of managing and searching large document collections and play a pivotal role in indexing electronic documents and building digital libraries. In this paper we explore a biomedical concept extraction technique based on a ranking algorithm of concept graphs. The proposed technique comprises two major steps: the first step is to represent documents with graphs whose nodes and edges are created by Named Entity Recognition and UMLS Semantic Network. The second step is rank concepts with relative importance algorithms. We evaluate our technique with a set of biomedical full-texts and compare it to various different key-phrase extraction and graph ranking techniques. The experimental results show that our technique achieves the best performance over other compared algorithms. We further take a close look at the properties of the network to examine how concepts are related to each other and what concept plays a dominant role in the network. To this end, we build the network with 526 full-text articles published in PubMed Central and measure the significance of nodes by centrality.",
author = "Min Song",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/35021BIGCOMP.2015.7072818",
language = "English",
pages = "103--110",
booktitle = "2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Song, M 2015, Exploring concept graphs for biomedical literature mining. in 2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015., 7072818, Institute of Electrical and Electronics Engineers Inc., pp. 103-110, 2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015, Jeju, Korea, Republic of, 15/2/9. https://doi.org/10.1109/35021BIGCOMP.2015.7072818

Exploring concept graphs for biomedical literature mining. / Song, Min.

2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 103-110 7072818.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Exploring concept graphs for biomedical literature mining

AU - Song, Min

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Full-text publications in an electronic form become more prevalent than ever before. It is a difficult challenge to extract concepts from unstructured document collections data because different concepts and their relationships are buried in them and ample term variations make the challenge compound. Extracted concepts are useful instruments of managing and searching large document collections and play a pivotal role in indexing electronic documents and building digital libraries. In this paper we explore a biomedical concept extraction technique based on a ranking algorithm of concept graphs. The proposed technique comprises two major steps: the first step is to represent documents with graphs whose nodes and edges are created by Named Entity Recognition and UMLS Semantic Network. The second step is rank concepts with relative importance algorithms. We evaluate our technique with a set of biomedical full-texts and compare it to various different key-phrase extraction and graph ranking techniques. The experimental results show that our technique achieves the best performance over other compared algorithms. We further take a close look at the properties of the network to examine how concepts are related to each other and what concept plays a dominant role in the network. To this end, we build the network with 526 full-text articles published in PubMed Central and measure the significance of nodes by centrality.

AB - Full-text publications in an electronic form become more prevalent than ever before. It is a difficult challenge to extract concepts from unstructured document collections data because different concepts and their relationships are buried in them and ample term variations make the challenge compound. Extracted concepts are useful instruments of managing and searching large document collections and play a pivotal role in indexing electronic documents and building digital libraries. In this paper we explore a biomedical concept extraction technique based on a ranking algorithm of concept graphs. The proposed technique comprises two major steps: the first step is to represent documents with graphs whose nodes and edges are created by Named Entity Recognition and UMLS Semantic Network. The second step is rank concepts with relative importance algorithms. We evaluate our technique with a set of biomedical full-texts and compare it to various different key-phrase extraction and graph ranking techniques. The experimental results show that our technique achieves the best performance over other compared algorithms. We further take a close look at the properties of the network to examine how concepts are related to each other and what concept plays a dominant role in the network. To this end, we build the network with 526 full-text articles published in PubMed Central and measure the significance of nodes by centrality.

UR - http://www.scopus.com/inward/record.url?scp=84928103764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928103764&partnerID=8YFLogxK

U2 - 10.1109/35021BIGCOMP.2015.7072818

DO - 10.1109/35021BIGCOMP.2015.7072818

M3 - Conference contribution

AN - SCOPUS:84928103764

SP - 103

EP - 110

BT - 2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Song M. Exploring concept graphs for biomedical literature mining. In 2015 International Conference on Big Data and Smart Computing, BIGCOMP 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 103-110. 7072818 https://doi.org/10.1109/35021BIGCOMP.2015.7072818