Enriching Graph Representations of Text: Application to Medical Text Classification

Alexios Mandalios; Alexandros Chortaras; Giorgos Stamou; Michalis Vazirgiannis

doi:10.1007/978-3-030-65351-4_8

Enriching Graph Representations of Text: Application to Medical Text Classification

Alexios Mandalios
, Alexandros Chortaras
, Giorgos Stamou
, Michalis Vazirgiannis

School of Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Graph based representations have been utilized to achieve state-of-the-art performance in text classification tasks. The same basic structure underlies knowledge graphs, large knowledge bases that contain rich information about the world. This paper capitalises on the graph of words model and enriches it with concepts from knowledge graphs, resulting in more powerful hybrid representations of a corpus. We focus on the domain of medical text classification and medical ontologies in order to test our proposed methods and analyze different alternatives in terms of text representation models and knowledge injection techniques. The method we present produces text representations that are both explainable and effective in improving the accuracy on the OHSUMED classification task, surpassing neural network architectures such as GraphStar and Text GCN.

Original language	English
Title of host publication	Complex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020
Editors	Rosa M. Benito, Chantal Cherifi, Hocine Cherifi, Esteban Moro, Luis Mateus Rocha, Marta Sales-Pardo
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	92-103
Number of pages	12
ISBN (Print)	9783030653507
DOIs	https://doi.org/10.1007/978-3-030-65351-4_8
Publication status	Published - 1 Jan 2021
Event	9th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2020 - Madrid, Spain Duration: 1 Dec 2020 → 3 Dec 2020

Publication series

Name	Studies in Computational Intelligence
Volume	944
ISSN (Print)	1860-949X
ISSN (Electronic)	1860-9503

Conference

Conference	9th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2020
Country/Territory	Spain
City	Madrid
Period	1/12/20 → 3/12/20

Keywords

Graph of words
Knowledge graphs
Medical information systems
Natural language processing
Semantic enrichment of text

Access to Document

10.1007/978-3-030-65351-4_8

Cite this

Mandalios, A., Chortaras, A., Stamou, G., & Vazirgiannis, M. (2021). Enriching Graph Representations of Text: Application to Medical Text Classification. In R. M. Benito, C. Cherifi, H. Cherifi, E. Moro, L. M. Rocha, & M. Sales-Pardo (Eds.), Complex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020 (pp. 92-103). (Studies in Computational Intelligence; Vol. 944). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-65351-4_8

Mandalios, Alexios ; Chortaras, Alexandros ; Stamou, Giorgos et al. / Enriching Graph Representations of Text : Application to Medical Text Classification. Complex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020. editor / Rosa M. Benito ; Chantal Cherifi ; Hocine Cherifi ; Esteban Moro ; Luis Mateus Rocha ; Marta Sales-Pardo. Springer Science and Business Media Deutschland GmbH, 2021. pp. 92-103 (Studies in Computational Intelligence).

@inproceedings{dd68bb339a974a4ba650a8e86c9eb9d2,

title = "Enriching Graph Representations of Text: Application to Medical Text Classification",

abstract = "Graph based representations have been utilized to achieve state-of-the-art performance in text classification tasks. The same basic structure underlies knowledge graphs, large knowledge bases that contain rich information about the world. This paper capitalises on the graph of words model and enriches it with concepts from knowledge graphs, resulting in more powerful hybrid representations of a corpus. We focus on the domain of medical text classification and medical ontologies in order to test our proposed methods and analyze different alternatives in terms of text representation models and knowledge injection techniques. The method we present produces text representations that are both explainable and effective in improving the accuracy on the OHSUMED classification task, surpassing neural network architectures such as GraphStar and Text GCN.",

keywords = "Graph of words, Knowledge graphs, Medical information systems, Natural language processing, Semantic enrichment of text",

author = "Alexios Mandalios and Alexandros Chortaras and Giorgos Stamou and Michalis Vazirgiannis",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 9th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2020 ; Conference date: 01-12-2020 Through 03-12-2020",

year = "2021",

month = jan,

day = "1",

doi = "10.1007/978-3-030-65351-4\_8",

language = "English",

isbn = "9783030653507",

series = "Studies in Computational Intelligence",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "92--103",

editor = "Benito, \{Rosa M.\} and Chantal Cherifi and Hocine Cherifi and Esteban Moro and Rocha, \{Luis Mateus\} and Marta Sales-Pardo",

booktitle = "Complex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020",

}

Mandalios, A, Chortaras, A, Stamou, G & Vazirgiannis, M 2021, Enriching Graph Representations of Text: Application to Medical Text Classification. in RM Benito, C Cherifi, H Cherifi, E Moro, LM Rocha & M Sales-Pardo (eds), Complex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020. Studies in Computational Intelligence, vol. 944, Springer Science and Business Media Deutschland GmbH, pp. 92-103, 9th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2020, Madrid, Spain, 1/12/20. https://doi.org/10.1007/978-3-030-65351-4_8

Enriching Graph Representations of Text: Application to Medical Text Classification. / Mandalios, Alexios; Chortaras, Alexandros; Stamou, Giorgos et al.
Complex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020. ed. / Rosa M. Benito; Chantal Cherifi; Hocine Cherifi; Esteban Moro; Luis Mateus Rocha; Marta Sales-Pardo. Springer Science and Business Media Deutschland GmbH, 2021. p. 92-103 (Studies in Computational Intelligence; Vol. 944).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Enriching Graph Representations of Text

T2 - 9th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2020

AU - Mandalios, Alexios

AU - Chortaras, Alexandros

AU - Stamou, Giorgos

AU - Vazirgiannis, Michalis

PY - 2021/1/1

Y1 - 2021/1/1

N2 - Graph based representations have been utilized to achieve state-of-the-art performance in text classification tasks. The same basic structure underlies knowledge graphs, large knowledge bases that contain rich information about the world. This paper capitalises on the graph of words model and enriches it with concepts from knowledge graphs, resulting in more powerful hybrid representations of a corpus. We focus on the domain of medical text classification and medical ontologies in order to test our proposed methods and analyze different alternatives in terms of text representation models and knowledge injection techniques. The method we present produces text representations that are both explainable and effective in improving the accuracy on the OHSUMED classification task, surpassing neural network architectures such as GraphStar and Text GCN.

AB - Graph based representations have been utilized to achieve state-of-the-art performance in text classification tasks. The same basic structure underlies knowledge graphs, large knowledge bases that contain rich information about the world. This paper capitalises on the graph of words model and enriches it with concepts from knowledge graphs, resulting in more powerful hybrid representations of a corpus. We focus on the domain of medical text classification and medical ontologies in order to test our proposed methods and analyze different alternatives in terms of text representation models and knowledge injection techniques. The method we present produces text representations that are both explainable and effective in improving the accuracy on the OHSUMED classification task, surpassing neural network architectures such as GraphStar and Text GCN.

KW - Graph of words

KW - Knowledge graphs

KW - Medical information systems

KW - Natural language processing

KW - Semantic enrichment of text

U2 - 10.1007/978-3-030-65351-4_8

DO - 10.1007/978-3-030-65351-4_8

M3 - Conference contribution

AN - SCOPUS:85101823991

SN - 9783030653507

T3 - Studies in Computational Intelligence

SP - 92

EP - 103

BT - Complex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020

A2 - Benito, Rosa M.

A2 - Cherifi, Chantal

A2 - Cherifi, Hocine

A2 - Moro, Esteban

A2 - Rocha, Luis Mateus

A2 - Sales-Pardo, Marta

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 1 December 2020 through 3 December 2020

ER -

Mandalios A, Chortaras A, Stamou G, Vazirgiannis M. Enriching Graph Representations of Text: Application to Medical Text Classification. In Benito RM, Cherifi C, Cherifi H, Moro E, Rocha LM, Sales-Pardo M, editors, Complex Networks and Their Applications IX - Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020. Springer Science and Business Media Deutschland GmbH. 2021. p. 92-103. (Studies in Computational Intelligence). doi: 10.1007/978-3-030-65351-4_8

Enriching Graph Representations of Text: Application to Medical Text Classification

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this