Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
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. | Automatically Generating Wikipedia Articles A Structure-Aware Approach Christina Sauper and Regina Barzilay Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology csauper regina @csail.mit.edu Abstract 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. 1 Introduction In this paper we consider the task of automatically creating a multi-paragraph overview article that provides a comprehensive summary of a subject of interest. Examples of such overviews include actor biographies from IMDB and disease synopses from Wikipedia. Producing these texts by hand is a labor-intensive task especially when relevant information is scattered throughout a wide range of Internet sources. Our goal is to automate this process. We aim to create an overview of a subject -e.g. 3-M Syndrome - by intelligently combining relevant excerpts from across the Internet. As a starting point we can employ methods developed for multi-document summarization. However our task poses additional technical challenges with respect to content planning. Generating a well-rounded overview article requires proactive strategies to gather relevant material such as searching the Internet. Moreover the challenge of maintaining output readability is magnified when .