Identifying gene and protein mentions in text using conditional random fields

Open Access

24 May 2005

journal article
Published by Springer Nature in BMC Bioinformatics

Vol. 6 (S1) , S6
https://doi.org/10.1186/1471-2105-6-s1-s6

Abstract

We present a model for tagging gene and protein mentions from text using the probabilistic sequence tagging framework of conditional random fields (CRFs). Conditional random fields model the probability P(t|o) of a tag sequence given an observation sequence directly, and have previously been employed successfully for other tagging tasks. The mechanics of CRFs and their relationship to maximum entropy are discussed in detail.

Keywords

This publication has 7 references indexed in Scilit:

A critical assessment of text mining methods in molecular biology. Proceedings of a workshop. March 28-31, 2004. Granada, Spain.
2005
A BIOLOGICAL NAMED ENTITY RECOGNIZER
Pacific Symposium on Biocomputing, 2002
Tagging gene and protein names in biomedical text
Bioinformatics, 2002
A survey of smoothing techniques for ME models
IEEE Transactions on Speech and Audio Processing, 2000
Numerical Optimization
Published by Springer Nature ,1999
A tutorial on hidden Markov models and selected applications in speech recognition
Proceedings of the IEEE, 1989
Generalized Iterative Scaling for Log-Linear Models
The Annals of Mathematical Statistics, 1972