MKEM

A multi-level knowledge emergence model for mining undiscovered public knowledge

Ali Zeeshan Ijaz, Min Song, Doheon Lee

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

Abstract

Since Swanson proposed the Undiscovered Public Knowledge (UPK) model, there have been many approaches to uncover UPK by mining the biomedical literature. These earlier works, however, required substantial manual intervention to reduce the number of possible connections and are mainly applied to disease-effect relation. With the advancement in biomedical science, it has become imperative to extract and combine information from multiple disjoint researches, studies and articles to infer new hypothesesand expand knowledge. In this paper, we propose MKEM, a Multi-level Knowledge Emergence Model, to discover implicit relationships using Natural Language Processing techniques such as Link Grammar and Ontologies such as Unified Medical Language System (UMLS) MetaMap. The contribution of MKEM is as follows: First, we propose a flexible knowledge emergence model to extract implicit relationships across different levels such as molecular level for gene and protein and Phenomic level for disease and treatment. Second, we employ MetaMap for tagging biological concepts. Third, we provide an empirical and systematic approach to discover novel relationships. Our experiments show that MKEM is a powerful tool to discover hidden relationships residing in extracted entities that were represented by our Substance-Effect-Process-Disease-Body Part (SEPDB) model.

Original languageEnglish
Title of host publication3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009
Pages51-58
Number of pages8
DOIs
Publication statusPublished - 2009 Dec 1
Event3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009 - Hong Kong, China
Duration: 2009 Nov 22009 Nov 6

Other

Other3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009
CountryChina
CityHong Kong
Period09/11/209/11/6

Fingerprint

Knowledge model
Ontology
Protein
Grammar
Experiment
Language
Tagging
Gene
Natural language processing

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Business, Management and Accounting(all)

Cite this

Ijaz, A. Z., Song, M., & Lee, D. (2009). MKEM: A multi-level knowledge emergence model for mining undiscovered public knowledge. In 3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009 (pp. 51-58) https://doi.org/10.1145/1651318.1651329
Ijaz, Ali Zeeshan ; Song, Min ; Lee, Doheon. / MKEM : A multi-level knowledge emergence model for mining undiscovered public knowledge. 3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009. 2009. pp. 51-58
@inproceedings{55d36857b35545b0b38b02e9713b89b2,
title = "MKEM: A multi-level knowledge emergence model for mining undiscovered public knowledge",
abstract = "Since Swanson proposed the Undiscovered Public Knowledge (UPK) model, there have been many approaches to uncover UPK by mining the biomedical literature. These earlier works, however, required substantial manual intervention to reduce the number of possible connections and are mainly applied to disease-effect relation. With the advancement in biomedical science, it has become imperative to extract and combine information from multiple disjoint researches, studies and articles to infer new hypothesesand expand knowledge. In this paper, we propose MKEM, a Multi-level Knowledge Emergence Model, to discover implicit relationships using Natural Language Processing techniques such as Link Grammar and Ontologies such as Unified Medical Language System (UMLS) MetaMap. The contribution of MKEM is as follows: First, we propose a flexible knowledge emergence model to extract implicit relationships across different levels such as molecular level for gene and protein and Phenomic level for disease and treatment. Second, we employ MetaMap for tagging biological concepts. Third, we provide an empirical and systematic approach to discover novel relationships. Our experiments show that MKEM is a powerful tool to discover hidden relationships residing in extracted entities that were represented by our Substance-Effect-Process-Disease-Body Part (SEPDB) model.",
author = "Ijaz, {Ali Zeeshan} and Min Song and Doheon Lee",
year = "2009",
month = "12",
day = "1",
doi = "10.1145/1651318.1651329",
language = "English",
isbn = "9781605588032",
pages = "51--58",
booktitle = "3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009",

}

Ijaz, AZ, Song, M & Lee, D 2009, MKEM: A multi-level knowledge emergence model for mining undiscovered public knowledge. in 3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009. pp. 51-58, 3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009, Hong Kong, China, 09/11/2. https://doi.org/10.1145/1651318.1651329

MKEM : A multi-level knowledge emergence model for mining undiscovered public knowledge. / Ijaz, Ali Zeeshan; Song, Min; Lee, Doheon.

3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009. 2009. p. 51-58.

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

TY - GEN

T1 - MKEM

T2 - A multi-level knowledge emergence model for mining undiscovered public knowledge

AU - Ijaz, Ali Zeeshan

AU - Song, Min

AU - Lee, Doheon

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Since Swanson proposed the Undiscovered Public Knowledge (UPK) model, there have been many approaches to uncover UPK by mining the biomedical literature. These earlier works, however, required substantial manual intervention to reduce the number of possible connections and are mainly applied to disease-effect relation. With the advancement in biomedical science, it has become imperative to extract and combine information from multiple disjoint researches, studies and articles to infer new hypothesesand expand knowledge. In this paper, we propose MKEM, a Multi-level Knowledge Emergence Model, to discover implicit relationships using Natural Language Processing techniques such as Link Grammar and Ontologies such as Unified Medical Language System (UMLS) MetaMap. The contribution of MKEM is as follows: First, we propose a flexible knowledge emergence model to extract implicit relationships across different levels such as molecular level for gene and protein and Phenomic level for disease and treatment. Second, we employ MetaMap for tagging biological concepts. Third, we provide an empirical and systematic approach to discover novel relationships. Our experiments show that MKEM is a powerful tool to discover hidden relationships residing in extracted entities that were represented by our Substance-Effect-Process-Disease-Body Part (SEPDB) model.

AB - Since Swanson proposed the Undiscovered Public Knowledge (UPK) model, there have been many approaches to uncover UPK by mining the biomedical literature. These earlier works, however, required substantial manual intervention to reduce the number of possible connections and are mainly applied to disease-effect relation. With the advancement in biomedical science, it has become imperative to extract and combine information from multiple disjoint researches, studies and articles to infer new hypothesesand expand knowledge. In this paper, we propose MKEM, a Multi-level Knowledge Emergence Model, to discover implicit relationships using Natural Language Processing techniques such as Link Grammar and Ontologies such as Unified Medical Language System (UMLS) MetaMap. The contribution of MKEM is as follows: First, we propose a flexible knowledge emergence model to extract implicit relationships across different levels such as molecular level for gene and protein and Phenomic level for disease and treatment. Second, we employ MetaMap for tagging biological concepts. Third, we provide an empirical and systematic approach to discover novel relationships. Our experiments show that MKEM is a powerful tool to discover hidden relationships residing in extracted entities that were represented by our Substance-Effect-Process-Disease-Body Part (SEPDB) model.

UR - http://www.scopus.com/inward/record.url?scp=74049100158&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74049100158&partnerID=8YFLogxK

U2 - 10.1145/1651318.1651329

DO - 10.1145/1651318.1651329

M3 - Conference contribution

SN - 9781605588032

SP - 51

EP - 58

BT - 3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009

ER -

Ijaz AZ, Song M, Lee D. MKEM: A multi-level knowledge emergence model for mining undiscovered public knowledge. In 3rd ACM International Workshop on Data and Text Mining in Bioinformatics, DTMBIO'09, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009. 2009. p. 51-58 https://doi.org/10.1145/1651318.1651329