Paper: Summarization by Analogy: An Example-based Approach for News Articles

ACL ID I08-2102
Title Summarization by Analogy: An Example-based Approach for News Articles
Venue International Joint Conference on Natural Language Processing
Session Main Conference
Year 2008
Authors

Automatic summarization is an important task as a form of human support technology. We propose in this paper a new summariza- tion method that is based on example-based approach. Using example-based approach for the summarization task has the following three advantages: high modularity, absence of the necessity to score importance for each word, and high applicability to local con- text. Experimental results have proven that the summarization system attains approxi- mately 60% accuracy by human judgment.