Knowledge node and relation detection

Jian Qin, Bei Yu, Liya Wang

Research output: Contribution to journalConference article

Abstract

A bottleneck problem in detecting knowledge nodes and their relations is how to extract accurately and correctly and codify the complex knowledge assertions from full-text documents (human intelligence) into the format of "machine intelligence" (computer-processable knowledge assertions). This paper reports a preliminary study that aims at this bottleneck problem by starting from the fundamentals of KR-representing knowledge from full-text documents by using knowledge node and relation recognition methods and tools. We collected data from full-text biomedical research publications and used manual and automatic tools to investigate the strengths and limitations of these methods. The findings show that MetaMap did a better job in detecting concepts from texts while SemRep is capable of extract relations between k-nodes. The paper presents the findings from the perspectives of degree of abstraction, types of k-nodes and relations, and linguistic structures and the evaluation results using the BLEU and cosine similarity measures.

Original languageEnglish (US)
Pages (from-to)29-44
Number of pages16
JournalCEUR Workshop Proceedings
Volume2200
StatePublished - Jan 1 2018
Event18th European Networked Knowledge Organization Systems Workshop, NKOS 2018 - Porto, Portugal
Duration: Sep 13 2018 → …

Fingerprint

Linguistics

Keywords

  • Knowledge node detection
  • Knowledge node relations
  • Knowledge representation
  • MetaMap
  • Relation recognition
  • SemRep.

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Knowledge node and relation detection. / Qin, Jian; Yu, Bei; Wang, Liya.

In: CEUR Workshop Proceedings, Vol. 2200, 01.01.2018, p. 29-44.

Research output: Contribution to journalConference article

@article{0908226dfaf64807926c973b66c53b5e,
title = "Knowledge node and relation detection",
abstract = "A bottleneck problem in detecting knowledge nodes and their relations is how to extract accurately and correctly and codify the complex knowledge assertions from full-text documents (human intelligence) into the format of {"}machine intelligence{"} (computer-processable knowledge assertions). This paper reports a preliminary study that aims at this bottleneck problem by starting from the fundamentals of KR-representing knowledge from full-text documents by using knowledge node and relation recognition methods and tools. We collected data from full-text biomedical research publications and used manual and automatic tools to investigate the strengths and limitations of these methods. The findings show that MetaMap did a better job in detecting concepts from texts while SemRep is capable of extract relations between k-nodes. The paper presents the findings from the perspectives of degree of abstraction, types of k-nodes and relations, and linguistic structures and the evaluation results using the BLEU and cosine similarity measures.",
keywords = "Knowledge node detection, Knowledge node relations, Knowledge representation, MetaMap, Relation recognition, SemRep.",
author = "Jian Qin and Bei Yu and Liya Wang",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "2200",
pages = "29--44",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

TY - JOUR

T1 - Knowledge node and relation detection

AU - Qin, Jian

AU - Yu, Bei

AU - Wang, Liya

PY - 2018/1/1

Y1 - 2018/1/1

N2 - A bottleneck problem in detecting knowledge nodes and their relations is how to extract accurately and correctly and codify the complex knowledge assertions from full-text documents (human intelligence) into the format of "machine intelligence" (computer-processable knowledge assertions). This paper reports a preliminary study that aims at this bottleneck problem by starting from the fundamentals of KR-representing knowledge from full-text documents by using knowledge node and relation recognition methods and tools. We collected data from full-text biomedical research publications and used manual and automatic tools to investigate the strengths and limitations of these methods. The findings show that MetaMap did a better job in detecting concepts from texts while SemRep is capable of extract relations between k-nodes. The paper presents the findings from the perspectives of degree of abstraction, types of k-nodes and relations, and linguistic structures and the evaluation results using the BLEU and cosine similarity measures.

AB - A bottleneck problem in detecting knowledge nodes and their relations is how to extract accurately and correctly and codify the complex knowledge assertions from full-text documents (human intelligence) into the format of "machine intelligence" (computer-processable knowledge assertions). This paper reports a preliminary study that aims at this bottleneck problem by starting from the fundamentals of KR-representing knowledge from full-text documents by using knowledge node and relation recognition methods and tools. We collected data from full-text biomedical research publications and used manual and automatic tools to investigate the strengths and limitations of these methods. The findings show that MetaMap did a better job in detecting concepts from texts while SemRep is capable of extract relations between k-nodes. The paper presents the findings from the perspectives of degree of abstraction, types of k-nodes and relations, and linguistic structures and the evaluation results using the BLEU and cosine similarity measures.

KW - Knowledge node detection

KW - Knowledge node relations

KW - Knowledge representation

KW - MetaMap

KW - Relation recognition

KW - SemRep.

UR - http://www.scopus.com/inward/record.url?scp=85053876694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053876694&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85053876694

VL - 2200

SP - 29

EP - 44

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -