A semantic system for answering questions in neuroinformatics

Aref Eshghishargh, Kathleen Gray, Simon K. Milton, Scott C. Kolbe

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

Abstract

Neuroinformatics is an important area of study in biomedical science and health informatics. Scientists in neuroscience tend to ask questions that are complicated, time consuming to answer and need multiple tasks in order to get to the result. In this paper, we introduce and report an ontology-based system for answering neuroscience questions automatically. The system uses a combination of ontologies such as NIFSTD and NeuroFMA, a template-based question translation method that translates questions to SparQL codes and MRI outputes (annotations) in order to classify and answer questions. It also uses an ontology-based query expansion module. The outcomes show the ontology-based question classification achieves 87.5% correct classification on the data set and the system can successfully answer 78.13% of questions. This research also uses machine learning techniques such as Naïve-Bayes, KNN, SVM and Random Forest to classify questions which respectively result in 54.54%, 68.18%, 72.72% and 77.27% correct classification.

Original languageEnglish
Title of host publicationProceedings of the Australasian Computer Science Week Multiconference 2018, Brisbane, Australia, ACSW 2018
EditorsMinh Ngoc Dinh
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Pages1-5
Number of pages5
ISBN (Electronic)9781450354363
DOIs
Publication statusPublished - 29 Jan 2018
Externally publishedYes
EventAustralasian Workshop on Health Informatics and Knowledge Management (HIKM) 2018 - Brisbane, Australia
Duration: 29 Jan 20182 Feb 2018
Conference number: 11th

Workshop

WorkshopAustralasian Workshop on Health Informatics and Knowledge Management (HIKM) 2018
Abbreviated titleHIKM 2018
CountryAustralia
CityBrisbane
Period29/01/182/02/18

Keywords

  • Neuroimaging
  • Neuroinformatics
  • Ontology
  • Question Answering
  • Question Classification

Cite this

Eshghishargh, A., Gray, K., Milton, S. K., & Kolbe, S. C. (2018). A semantic system for answering questions in neuroinformatics. In M. N. Dinh (Ed.), Proceedings of the Australasian Computer Science Week Multiconference 2018, Brisbane, Australia, ACSW 2018 (pp. 1-5). [3167960] New York NY USA: Association for Computing Machinery (ACM). https://doi.org/10.1145/3167918.3167960
Eshghishargh, Aref ; Gray, Kathleen ; Milton, Simon K. ; Kolbe, Scott C. / A semantic system for answering questions in neuroinformatics. Proceedings of the Australasian Computer Science Week Multiconference 2018, Brisbane, Australia, ACSW 2018. editor / Minh Ngoc Dinh. New York NY USA : Association for Computing Machinery (ACM), 2018. pp. 1-5
@inproceedings{34b4c1477a6e44af8a0a351de0f44068,
title = "A semantic system for answering questions in neuroinformatics",
abstract = "Neuroinformatics is an important area of study in biomedical science and health informatics. Scientists in neuroscience tend to ask questions that are complicated, time consuming to answer and need multiple tasks in order to get to the result. In this paper, we introduce and report an ontology-based system for answering neuroscience questions automatically. The system uses a combination of ontologies such as NIFSTD and NeuroFMA, a template-based question translation method that translates questions to SparQL codes and MRI outputes (annotations) in order to classify and answer questions. It also uses an ontology-based query expansion module. The outcomes show the ontology-based question classification achieves 87.5{\%} correct classification on the data set and the system can successfully answer 78.13{\%} of questions. This research also uses machine learning techniques such as Na{\"i}ve-Bayes, KNN, SVM and Random Forest to classify questions which respectively result in 54.54{\%}, 68.18{\%}, 72.72{\%} and 77.27{\%} correct classification.",
keywords = "Neuroimaging, Neuroinformatics, Ontology, Question Answering, Question Classification",
author = "Aref Eshghishargh and Kathleen Gray and Milton, {Simon K.} and Kolbe, {Scott C.}",
year = "2018",
month = "1",
day = "29",
doi = "10.1145/3167918.3167960",
language = "English",
pages = "1--5",
editor = "Dinh, {Minh Ngoc }",
booktitle = "Proceedings of the Australasian Computer Science Week Multiconference 2018, Brisbane, Australia, ACSW 2018",
publisher = "Association for Computing Machinery (ACM)",
address = "United States of America",

}

Eshghishargh, A, Gray, K, Milton, SK & Kolbe, SC 2018, A semantic system for answering questions in neuroinformatics. in MN Dinh (ed.), Proceedings of the Australasian Computer Science Week Multiconference 2018, Brisbane, Australia, ACSW 2018., 3167960, Association for Computing Machinery (ACM), New York NY USA, pp. 1-5, Australasian Workshop on Health Informatics and Knowledge Management (HIKM) 2018, Brisbane, Australia, 29/01/18. https://doi.org/10.1145/3167918.3167960

A semantic system for answering questions in neuroinformatics. / Eshghishargh, Aref; Gray, Kathleen; Milton, Simon K.; Kolbe, Scott C.

Proceedings of the Australasian Computer Science Week Multiconference 2018, Brisbane, Australia, ACSW 2018. ed. / Minh Ngoc Dinh. New York NY USA : Association for Computing Machinery (ACM), 2018. p. 1-5 3167960.

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

TY - GEN

T1 - A semantic system for answering questions in neuroinformatics

AU - Eshghishargh, Aref

AU - Gray, Kathleen

AU - Milton, Simon K.

AU - Kolbe, Scott C.

PY - 2018/1/29

Y1 - 2018/1/29

N2 - Neuroinformatics is an important area of study in biomedical science and health informatics. Scientists in neuroscience tend to ask questions that are complicated, time consuming to answer and need multiple tasks in order to get to the result. In this paper, we introduce and report an ontology-based system for answering neuroscience questions automatically. The system uses a combination of ontologies such as NIFSTD and NeuroFMA, a template-based question translation method that translates questions to SparQL codes and MRI outputes (annotations) in order to classify and answer questions. It also uses an ontology-based query expansion module. The outcomes show the ontology-based question classification achieves 87.5% correct classification on the data set and the system can successfully answer 78.13% of questions. This research also uses machine learning techniques such as Naïve-Bayes, KNN, SVM and Random Forest to classify questions which respectively result in 54.54%, 68.18%, 72.72% and 77.27% correct classification.

AB - Neuroinformatics is an important area of study in biomedical science and health informatics. Scientists in neuroscience tend to ask questions that are complicated, time consuming to answer and need multiple tasks in order to get to the result. In this paper, we introduce and report an ontology-based system for answering neuroscience questions automatically. The system uses a combination of ontologies such as NIFSTD and NeuroFMA, a template-based question translation method that translates questions to SparQL codes and MRI outputes (annotations) in order to classify and answer questions. It also uses an ontology-based query expansion module. The outcomes show the ontology-based question classification achieves 87.5% correct classification on the data set and the system can successfully answer 78.13% of questions. This research also uses machine learning techniques such as Naïve-Bayes, KNN, SVM and Random Forest to classify questions which respectively result in 54.54%, 68.18%, 72.72% and 77.27% correct classification.

KW - Neuroimaging

KW - Neuroinformatics

KW - Ontology

KW - Question Answering

KW - Question Classification

UR - http://www.scopus.com/inward/record.url?scp=85044789546&partnerID=8YFLogxK

U2 - 10.1145/3167918.3167960

DO - 10.1145/3167918.3167960

M3 - Conference Paper

SP - 1

EP - 5

BT - Proceedings of the Australasian Computer Science Week Multiconference 2018, Brisbane, Australia, ACSW 2018

A2 - Dinh, Minh Ngoc

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

ER -

Eshghishargh A, Gray K, Milton SK, Kolbe SC. A semantic system for answering questions in neuroinformatics. In Dinh MN, editor, Proceedings of the Australasian Computer Science Week Multiconference 2018, Brisbane, Australia, ACSW 2018. New York NY USA: Association for Computing Machinery (ACM). 2018. p. 1-5. 3167960 https://doi.org/10.1145/3167918.3167960