Automatically Generating Wikipedia Articles: A Structure-Aware Approach

In this paper, we investigate an approach for creating a comprehensive textual overview of a subject composed of information drawn from the Internet. We use the high-level structure of human-authored texts to automatically induce a domainspecific template for the topic structure of a new overview. The algorithmic innovation of our work is a method to learn topicspecific extractors for content selection jointly for the entire template. We augment the standard perceptron algorithm with a global integer linear programming formulation to optimize both local fit of information into each topic and global coherence across the entire overview. The results of our evaluation confirm the benefits of incorporating structural information into the content selection process.

• Type: Journal
• Year: 2009
• Where: ACL
• Authors: Christina Sauper, Regina Barzilay
• Keywords: ACL 2009, Comprehensive Textual Overview, Computational Linguistics, Content Selection, Standard Perceptron Algorithm