Improving named entity recognition accuracy for gene and protein in biomedical text literature
The task of recognising biomedical named entities in natural language documents called biomedical Named Entity Recognition (NER) is the focus of many researchers due to complex nature of such texts. This complexity includes the issues of character-level, word-level and word order variations. In this...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Inderscience Publishers
2014
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/37986/1/Improving%20named%20entity%20recognition%20accuracy%20for%20gene%20and%20protein%20in%20biomedical%20text%20literature.pdf |
| _version_ | 1825949137701437440 |
|---|---|
| author | Tohidi, Hossein Ibrahim, Hamidah Azmi Murad, Masrah Azrifah |
| author_facet | Tohidi, Hossein Ibrahim, Hamidah Azmi Murad, Masrah Azrifah |
| author_sort | Tohidi, Hossein |
| collection | UPM |
| description | The task of recognising biomedical named entities in natural language documents called biomedical Named Entity Recognition (NER) is the focus of many researchers due to complex nature of such texts. This complexity includes the issues of character-level, word-level and word order variations. In this study, an approach for recognising gene and protein names that handles the above issues is proposed. Similar to the previous related works, our approach is based on the assumption that a named entity occurs within a noun group. The strength of our proposed approach lies on a Statistical Character-based Syntax Similarity (SCSS) algorithm which measures similarity between the extracted candidates and the well-known biomedical named entities from the GENIA V3.0 corpus. The proposed approach is evaluated and results are satisfied. For recognitions of both gene and protein names, we achieved 97.2% for precision (P), 95.2% for recall (R), and 96.1 for F-measure. While for protein names recognition we gained 98.1% for P, 97.5% for R and 97.7 for F-measure. |
| first_indexed | 2024-03-06T08:39:57Z |
| format | Article |
| id | upm.eprints-37986 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T08:39:57Z |
| publishDate | 2014 |
| publisher | Inderscience Publishers |
| record_format | dspace |
| spelling | upm.eprints-379862015-12-29T09:05:27Z http://psasir.upm.edu.my/id/eprint/37986/ Improving named entity recognition accuracy for gene and protein in biomedical text literature Tohidi, Hossein Ibrahim, Hamidah Azmi Murad, Masrah Azrifah The task of recognising biomedical named entities in natural language documents called biomedical Named Entity Recognition (NER) is the focus of many researchers due to complex nature of such texts. This complexity includes the issues of character-level, word-level and word order variations. In this study, an approach for recognising gene and protein names that handles the above issues is proposed. Similar to the previous related works, our approach is based on the assumption that a named entity occurs within a noun group. The strength of our proposed approach lies on a Statistical Character-based Syntax Similarity (SCSS) algorithm which measures similarity between the extracted candidates and the well-known biomedical named entities from the GENIA V3.0 corpus. The proposed approach is evaluated and results are satisfied. For recognitions of both gene and protein names, we achieved 97.2% for precision (P), 95.2% for recall (R), and 96.1 for F-measure. While for protein names recognition we gained 98.1% for P, 97.5% for R and 97.7 for F-measure. Inderscience Publishers 2014 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/37986/1/Improving%20named%20entity%20recognition%20accuracy%20for%20gene%20and%20protein%20in%20biomedical%20text%20literature.pdf Tohidi, Hossein and Ibrahim, Hamidah and Azmi Murad, Masrah Azrifah (2014) Improving named entity recognition accuracy for gene and protein in biomedical text literature. International Journal of Data Mining and Bioinformatics, 10 (3). pp. 239-268. ISSN 1748-5673; ESSN: 1748-5681 http://www.inderscienceonline.com/doi/abs/10.1504/IJDMB.2014.064523 10.1504/IJDMB.2014.064523 |
| spellingShingle | Tohidi, Hossein Ibrahim, Hamidah Azmi Murad, Masrah Azrifah Improving named entity recognition accuracy for gene and protein in biomedical text literature |
| title | Improving named entity recognition accuracy for gene and protein in biomedical text literature |
| title_full | Improving named entity recognition accuracy for gene and protein in biomedical text literature |
| title_fullStr | Improving named entity recognition accuracy for gene and protein in biomedical text literature |
| title_full_unstemmed | Improving named entity recognition accuracy for gene and protein in biomedical text literature |
| title_short | Improving named entity recognition accuracy for gene and protein in biomedical text literature |
| title_sort | improving named entity recognition accuracy for gene and protein in biomedical text literature |
| url | http://psasir.upm.edu.my/id/eprint/37986/1/Improving%20named%20entity%20recognition%20accuracy%20for%20gene%20and%20protein%20in%20biomedical%20text%20literature.pdf |
| work_keys_str_mv | AT tohidihossein improvingnamedentityrecognitionaccuracyforgeneandproteininbiomedicaltextliterature AT ibrahimhamidah improvingnamedentityrecognitionaccuracyforgeneandproteininbiomedicaltextliterature AT azmimuradmasrahazrifah improvingnamedentityrecognitionaccuracyforgeneandproteininbiomedicaltextliterature |