생의학 분야 학술 논문에서의 개체명 인식 및 관계 추출을 위한 언어 자원 수집 및 통합적 구조화 방안 연구 (A Study on Collecting and Structuring Language Resource for Named Entity Recognition and Relation Extraction from Biomedical Abstracts)

강슬기 (Seul-ki Kang); 최윤수; 최성필 (Sung-Pil Choi)

doi:10.4275/KSLIS.2017.51.4.227

A Study on Collecting and Structuring Language Resource for Named Entity Recognition and Relation Extraction from Biomedical Abstracts

Journal of the Korean Society for Library and Information Science
2017, 51(4), pp.227-248
DOI : 10.4275/KSLIS.2017.51.4.227
Publisher : 한국문헌정보학회
Research Area : Interdisciplinary Studies > Library and Information Science

Seul-ki Kang ¹, 최윤수 ², Sung-Pil Choi ¹

¹경기대학교
²한국과학기술정보연구원

Accredited

ABSTRACT

This paper introduces an integrated model for systematically constructing a linguistic resource database that can be used by machine learning-based biomedical information extraction systems. The proposed method suggests an orderly process of collecting and constructing dictionaries and training sets for both named-entity recognition and relation extraction. Multiple heterogeneous structures for the resources which are collected from diverse sources are analyzed to derive essential items and fields for constructing the integrated database. All the collected resources are converted and refined to build an integrated linguistic resource storage. In this paper, we constructed entity dictionaries of gene, protein, disease and drug, which are considered core linguistic elements or core named entities in the biomedical domains and conducted verification tests to measure their acceptability.

KEYWORDS

Information Extraction, Named-Entity Recognition, Relation Extraction, Bio-text Mining, Training Set

Citation status

* References for papers published after 2023 are currently being built.

[journal] 박성배 / 2005 / 기계학습/텍스트마이닝과 생명과학 / 정보과학회지 23(5) : 32~40

[journal] 박경미 / 2011 / A Bio-Text Mining System Based on Natural Language Processing / 정보과학회 컴퓨팅의 실제 논문지 / 한국정보과학회 17(4) : 205~213

[journal] 송영길 / 2015 / A Semi-automatic Construction method of a Named Entity Dictionary Based on Wikipedia / 정보과학회논문지 / 한국정보과학회 42(11) : 1397~1403

[journal] 신성호 / 2014 / Construction of Tagged Corpus and a Statistical Model for Improvement of Named Entity Recognition / 정보과학회 컴퓨팅의 실제 논문지 / 한국정보과학회 20(7) : 425~429

[confproc] 이혜진 / 2017 / 자연어 처리 기술 현황 및 표준화 동향에 관한 연구 / 한국통신학회 학술대회논문집 : 876~877

[journal] 허고은 / 2014 / Inferring Undiscovered Public Knowledge by Using Text Mining-driven Graph Model / 정보관리학회지 / 한국정보관리학회 31(1) : 231~250

[journal] Ananiadou, S. / 2006 / Text Mining and Its Potential Applications in Systems Biology / Trends in Biotechnology 24(12) : 571~579

[journal] Beuning, P. / 1999 / Transfer RNA Recognition by Aminoacyl-tRNA Synthetases / Biopolymers 52(1) : 1~28

[web] / 2017 / Biomedical Informatics Lab at ASU / Arizona Disease Corpus / http://diego.asu.edu

[journal] Choi, S / 2016 / Extraction of Protein-Protein Interactions(PPIs)from the Literature by Deep Convolutional Neural Networks with Various Feature Embeddings / Sage Journals : 2016~

[web] / 2017 / Comparative Toxicogenomics Database / Gene vocabulary / http://ctdbase.org/;jsessionid=0868DE4D459374D22AB222F9CC3ECA43

[web] DrugBank / 2017 / COMPLETE DATABASE: All drugs / https://www.drugbank.ca/

[web] Fraunhofer Institute for Algorithms and Scientific Computing SCAI / 2017 / Silver Standard Corpus for Protein Protein and Drug Drug Interaction / https://www.scai.fraunhofer.de/en.html

[web] / 2017 / GENIA: The BioNLP Shared Task 2016 / The BioNLP Shared Task / http://2016.bionlp-st.org/

[journal] Huang, C. / 2016 / Community Challenges in Biomedical Text Mining over 10 years : Success, Failure and the Future / Briefings in Bioinformatics 17(1) : 132~144

[web] HUGO Gene Nomenclature Committee / 2017 / Complete HGNC Dataset / https://www.genenames.org/

[journal] Jensen, L. J. / 2006 / Literature Mining for the Biologist : from Information Retrieval to Biological Discovery / Nature Reviews Genetics 7(2) : 119~129

[confproc] Kim, J. / 2013 / The Genia Event Extraction Shared Task, 2013Edition-Overview / Proceedings of the BioNLP Shared Task 2013 Workshop / Association for Computational Linguistics

[web] / 2017 / National Center for Biotechnology Information / PubMed / https://www.ncbi.nlm.nih.gov/

[web] / 2017 / National Institutes of Health / Genetic Association Database / https://www.nih.gov/

[web] Natural Language Toolkit / 2017 / Natural Language Processing with Python / http://www.nltk.org/

[web] The National Centre for Text Mining / 2016 / Text Mining Resources / http://www.nactem.ac.uk/resources.php

[web] The University of Pittsburgh Pharmacokinetic Drug-drug Interation (PK DDI) Package Insert Corpus / 2017 / Download the PK-DDI corpus with consensus annotations / https://dbmi-icode-01.dbmi.pitt.edu/dikb-evidence/package-insert-DDI-NLP-corpus.html

[web] / 2017 / tagtog / LocText / https://www.tagtog.net/

[confproc] Thomas, P / 2012 / Weakly labeled corpora as silver standard for drug-drug and proteinprotein interaction / Proceedings of the Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM) on Language Resources and Evaluation Conference (LREC)

[journal] Tripathi, V. / 2010 / The Nuclear-Retained Noncoding RNA MALAT1 Regulates Alternative Splicing by Modulating SR Splicing Factor Phosphorylation / Molecular Cell 39(6) : 925~938

[web] UniProt. / 2017 / Uniprot data / http://www.uniprot.org/

KJCKorea
Journal Central

Journal of the Korean Society for Library and Information Science 2023 KCI Impact Factor : 0.84

A Study on Collecting and Structuring Language Resource for Named Entity Recognition and Relation Extraction from Biomedical Abstracts

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of the Korean Society for Library and Information Science 2023 KCI Impact Factor : 0.84

A Study on Collecting and Structuring Language Resource for Named Entity Recognition and Relation Extraction from Biomedical Abstracts

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (2)

REFERENCES (27) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.