Abstract
BackgroundWe 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.ResultsWe employ a diverse feature set containing standard orthographic features combined with expert features in the form of gene and biological term lexicons to achieve a precision of 86.4% and recall of 78.7%. An analysis of the contribution of the various features of the model is provided.
Highlights
We present a model for tagging gene and protein mentions from text using the probabilistic sequence tagging framework of conditional random fields (CRFs)
The first step in most information extraction systems is to identify the named entities that are relevant to the concepts, relations and events described in the text
In molecular biology, named entities related to genes, proteins or other biologically-active molecules are especially important
Summary
We present a model for tagging gene and protein mentions from text using the probabilistic sequence tagging framework of conditional random fields (CRFs). The first step in most information extraction systems is to identify the named entities that are relevant to the concepts, relations and events described in the text. We present here a method for identifying gene and protein mentions in text with conditional random fields (CRFs) [6], which are discussed . Our method does just this by turning many of the post-processing steps of Tanabe and Wilbur [5] into features used in the extraction CRF. This is a single probabilistic tagging model with no application-specific pre- or post-processing steps or voting over multiple classifiers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
