Exploiting and integrating rich features for biological literature classification

Hongning Wang,Xiaoyan Zhu,Shilin Ding,Minlie Huang

doi:10.1186/1471-2105-9-s3-s4

Abstract

BackgroundEfficient features play an important role in automated text classification, which definitely facilitates the access of large-scale data. In the bioscience field, biological structures and terminologies are described by a large number of features; domain dependent features would significantly improve the classification performance. How to effectively select and integrate different types of features to improve the biological literature classification performance is the major issue studied in this paper.ResultsTo efficiently classify the biological literatures, we propose a novel feature value schema TF*ML, features covering from lower level domain independent “string feature” to higher level domain dependent “semantic template feature”, and proper integrations among the features. Compared to our previous approaches, the performance is improved in terms of AUC and F-Score by 11.5% and 8.8% respectively, and outperforms the best performance achieved in BioCreAtIvE 2006.ConclusionsDifferent types of features possess different discriminative capabilities in literature classification; proper integration of domain independent and dependent features would significantly improve the performance and overcome the over-fitting on data distribution.

Highlights

Efficient features play an important role in automated text classification, which definitely facilitates the access of large-scale data
We investigate the issue of biological literature classification from the perspective of feature selection and integration, which is evaluated by BioCreAtIvE [10], an international evaluation in biological text mining
The experiment results clearly demonstrate that the lower level features are endowed with better generalization capability, but hampered by lower accuracy; higher level features contain rich domain dependent information, with better specificity but poor universality

Summary

Introduction

Efficient features play an important role in automated text classification, which definitely facilitates the access of large-scale data. Biological structures and terminologies are described by a large number of features; domain dependent features would significantly improve the classification performance. Regev et al used expert-defined rules to extract features from the semi-structure text and figure legends They utilized external lexical resources and semantic constraints to achieve a better coverage and accuracy [3]. Ghanem et al utilized expert-edited regular expressions to capture frequently occurring keyword combinations (or motifs) within short segments of the text in a document [5] All these approaches require the involvement of domain experts in identifying the specific textual objects and the informative templates, so that they cannot be automatically extended to an efficient and scalefree model on other biological datasets [6]

Methods

Results

Conclusion