Biomedical text categorization with concept graph representations using a controlled vocabulary

Meenakshi Mishra; Jun Huan; Said Bleik; Min Song

doi:10.1145/2350176.2350181

Biomedical text categorization with concept graph representations using a controlled vocabulary

Meenakshi Mishra, Jun Huan, Said Bleik, Min Song

Department of Library and Information Science

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

11 Citations (Scopus)

Abstract

Recent work using graph representations for text categorization has shown promising performance over conventional bag-of-words representation of text documents. In this paper we investigate a graph representation of texts for the task of text categorization. In our representation we identify high level concepts extracted from a database of controlled biomedical terms and build a rich graph structure that contains important concepts and relationships. This procedure ensures that graphs are described with a regular vocabulary, leading to increased ease of comparison. We then classify document graphs by applying a set-based graph kernel that is intuitively sensible and able to deal with the disconnectedness of the constructed concept graphs. We compare this approach to standard approaches using non-graph, text-based features. We also do a comparison amongst different kernels that can be used to see which performs better.

Original language	English
Title of host publication	Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12
Pages	26-32
Number of pages	7
DOIs	https://doi.org/10.1145/2350176.2350181
Publication status	Published - 2012
Event	11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12 - Beijing, China Duration: 2012 Aug 12 → 2012 Aug 12

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Other

Other	11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12
Country/Territory	China
City	Beijing
Period	12/8/12 → 12/8/12

All Science Journal Classification (ASJC) codes

Software
Information Systems

Access to Document

10.1145/2350176.2350181

Cite this

Mishra, M., Huan, J., Bleik, S., & Song, M. (2012). Biomedical text categorization with concept graph representations using a controlled vocabulary. In Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12 (pp. 26-32). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). https://doi.org/10.1145/2350176.2350181

Mishra, Meenakshi ; Huan, Jun ; Bleik, Said et al. / Biomedical text categorization with concept graph representations using a controlled vocabulary. Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12. 2012. pp. 26-32 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{abbab2138358470ebdf2be59761748ad,

title = "Biomedical text categorization with concept graph representations using a controlled vocabulary",

abstract = "Recent work using graph representations for text categorization has shown promising performance over conventional bag-of-words representation of text documents. In this paper we investigate a graph representation of texts for the task of text categorization. In our representation we identify high level concepts extracted from a database of controlled biomedical terms and build a rich graph structure that contains important concepts and relationships. This procedure ensures that graphs are described with a regular vocabulary, leading to increased ease of comparison. We then classify document graphs by applying a set-based graph kernel that is intuitively sensible and able to deal with the disconnectedness of the constructed concept graphs. We compare this approach to standard approaches using non-graph, text-based features. We also do a comparison amongst different kernels that can be used to see which performs better.",

author = "Meenakshi Mishra and Jun Huan and Said Bleik and Min Song",

year = "2012",

doi = "10.1145/2350176.2350181",

language = "English",

isbn = "9781450315524",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

pages = "26--32",

booktitle = "Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12",

note = "11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12 ; Conference date: 12-08-2012 Through 12-08-2012",

}

Mishra, M, Huan, J, Bleik, S & Song, M 2012, Biomedical text categorization with concept graph representations using a controlled vocabulary. in Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 26-32, 11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12, Beijing, China, 12/8/12. https://doi.org/10.1145/2350176.2350181

Biomedical text categorization with concept graph representations using a controlled vocabulary. / Mishra, Meenakshi; Huan, Jun; Bleik, Said et al.
Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12. 2012. p. 26-32 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

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

TY - GEN

T1 - Biomedical text categorization with concept graph representations using a controlled vocabulary

AU - Mishra, Meenakshi

AU - Huan, Jun

AU - Bleik, Said

AU - Song, Min

PY - 2012

Y1 - 2012

N2 - Recent work using graph representations for text categorization has shown promising performance over conventional bag-of-words representation of text documents. In this paper we investigate a graph representation of texts for the task of text categorization. In our representation we identify high level concepts extracted from a database of controlled biomedical terms and build a rich graph structure that contains important concepts and relationships. This procedure ensures that graphs are described with a regular vocabulary, leading to increased ease of comparison. We then classify document graphs by applying a set-based graph kernel that is intuitively sensible and able to deal with the disconnectedness of the constructed concept graphs. We compare this approach to standard approaches using non-graph, text-based features. We also do a comparison amongst different kernels that can be used to see which performs better.

AB - Recent work using graph representations for text categorization has shown promising performance over conventional bag-of-words representation of text documents. In this paper we investigate a graph representation of texts for the task of text categorization. In our representation we identify high level concepts extracted from a database of controlled biomedical terms and build a rich graph structure that contains important concepts and relationships. This procedure ensures that graphs are described with a regular vocabulary, leading to increased ease of comparison. We then classify document graphs by applying a set-based graph kernel that is intuitively sensible and able to deal with the disconnectedness of the constructed concept graphs. We compare this approach to standard approaches using non-graph, text-based features. We also do a comparison amongst different kernels that can be used to see which performs better.

UR - http://www.scopus.com/inward/record.url?scp=84866635017&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866635017&partnerID=8YFLogxK

U2 - 10.1145/2350176.2350181

DO - 10.1145/2350176.2350181

M3 - Conference contribution

AN - SCOPUS:84866635017

SN - 9781450315524

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 26

EP - 32

BT - Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12

T2 - 11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12

Y2 - 12 August 2012 through 12 August 2012

ER -

Mishra M, Huan J, Bleik S, Song M. Biomedical text categorization with concept graph representations using a controlled vocabulary. In Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12. 2012. p. 26-32. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/2350176.2350181

Biomedical text categorization with concept graph representations using a controlled vocabulary

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this