University of Wisconsin, Milwaukee, Milwaukee WI 53211, USA.
Bioinformatics. 2009 Dec 1;25(23):3174-80. doi: 10.1093/bioinformatics/btp548. Epub 2009 Sep 25.
Biomedical texts can be typically represented by four rhetorical categories: Introduction, Methods, Results and Discussion (IMRAD). Classifying sentences into these categories can benefit many other text-mining tasks. Although many studies have applied different approaches for automatically classifying sentences in MEDLINE abstracts into the IMRAD categories, few have explored the classification of sentences that appear in full-text biomedical articles. We first evaluated whether sentences in full-text biomedical articles could be reliably annotated into the IMRAD format and then explored different approaches for automatically classifying these sentences into the IMRAD categories. Our results show an overall annotation agreement of 82.14% with a Kappa score of 0.756. The best classification system is a multinomial naïve Bayes classifier trained on manually annotated data that achieved 91.95% accuracy and an average F-score of 91.55%, which is significantly higher than baseline systems. A web version of this system is available online at-http://wood.ims.uwm.edu/full_text_classifier/.
引言、方法、结果和讨论（IMRAD）。将句子分类为这些类别可以有益于许多其他文本挖掘任务。尽管许多研究已经应用了不同的方法来自动将 MEDLINE 摘要中的句子分类为 IMRAD 类别，但很少有研究探索将出现在全文生物医学文章中的句子进行分类。我们首先评估了全文生物医学文章中的句子是否可以可靠地注释为 IMRAD 格式，然后探索了自动将这些句子分类为 IMRAD 类别的不同方法。我们的结果显示，整体注释一致性为 82.14%，kappa 得分为 0.756。最佳分类系统是基于手动注释数据训练的多项式朴素贝叶斯分类器，其准确率为 91.95%，平均 F1 得分为 91.55%，明显高于基线系统。该系统的网络版本可在-http://wood.ims.uwm.edu/full_text_classifier/ 上获得。
