Enhancing performance of protein and gene name recognizers with filtering and integration strategies

Wen Juan Hou, Hsin Hsi Chen

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)


Named entity (NE) recognition is a fundamental task in biological relationship mining. This paper considers protein/gene collocates extracted from biological corpora as restrictions to enhance the precision rate of protein/gene name recognition. In addition, we integrate the results of multiple NE recognizers to improve the recall rates. Yapex and KeX, and ABGene and Idgene are taken as examples of protein and gene name recognizers, respectively. The precision of Yapex increases from 70.90 to 85.84% at the low expense of the recall rate (i.e., it only decreases 2.44%) when collocates are incorporated. When both filtering and integration strategies are employed together, the Yapex-based integration with KeX shows good performance, i.e., the F-score increases by 7.83% compared to the pure Yapex method. The results of gene recognition show the same tendency. The ABGene-based integration with Idgene shows a 10.18% F-score increase compared to the pure ABGene method. These successful methodologies can be easily extended to other name finders in biological documents.

Original languageEnglish
Pages (from-to)448-460
Number of pages13
JournalJournal of Biomedical Informatics
Issue number6
Publication statusPublished - 2004 Dec
Externally publishedYes


  • Biological keywords
  • Collocation model
  • Gene name recognition
  • Protein name recognition
  • t test

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics


Dive into the research topics of 'Enhancing performance of protein and gene name recognizers with filtering and integration strategies'. Together they form a unique fingerprint.

Cite this