Statistical algorithms for ontology-based annotation of scientific literature

Authors

Chayan Chakrabarti, University of New Mexico
Thomas B. Jones, University of New Mexico
George F. Luger, Department of Computer Science, University of New Mexico
Jiawei F. Xu, Department of Computer Science, University of New MexicoFollow
Matthew D. Turner, Department of Computer Science, University of New MexicoFollow
Angela R. Laird, Department of Physics, Florida International UniversityFollow
Jessica A. Turner, Mind Research Network; Department of Psychology and the Neuroscience Institute, Georgia State UniversityFollow

Date of this Version

6-3-2014

Document Type

Article

Abstract

Background

Ontologies encode relationships within a domain in robust data structures that can be used to annotate data objects, including scientific papers, in ways that ease tasks such as search and meta-analysis. However, the annotation process requires significant time and effort when performed by humans. Text mining algorithms can facilitate this process, but they render an analysis mainly based upon keyword, synonym and semantic matching. They do not leverage information embedded in an ontology's structure.

Methods

We present a probabilistic framework that facilitates the automatic annotation of literature by indirectly modeling the restrictions among the different classes in the ontology. Our research focuses on annotating human functional neuroimaging literature within the Cognitive Paradigm Ontology (CogPO). We use an approach that combines the stochastic simplicity of naïve Bayes with the formal transparency of decision trees. Our data structure is easily modifiable to reflect changing domain knowledge.

Results

We compare our results across naïve Bayes, Bayesian Decision Trees, and Constrained Decision Tree classifiers that keep a human expert in the loop, in terms of the quality measure of the F1-mirco score.

Conclusions

Unlike traditional text mining algorithms, our framework can model the knowledge encoded by the dependencies in an ontology, albeit indirectly. We successfully exploit the fact that CogPO has explicitly stated restrictions, and implicit dependencies in the form of patterns in the expert curated annotations.

Creative Commons License

This work is licensed under a Creative Commons Attribution 2.0 License.

Comments

Originally published in Journal of Biomedical Semantics.

Recommended Citation

Chakrabarti et al.: Statistical algorithms for ontology-based annotation of scientific literature. Journal of Biomedical Semantics 2014 5(Suppl 1):S2.