A Symbolic Summarizer for the Update Task of TAC 2008
Pierre-Étienne Genest, Guy Lapalme, Luka Nerima, Éric Wehrli · 2008
NESS, RALI’s summarization system for the TAC 2008’s update task, brings improvements and continuation to our last year’s “all-symbolic ” approach. The most distinctive feature of our system is to rely on the syntactical parser FIPS to extract linguistic knowledge from source documents. NESS selects sentences based on linguistic metrics, especially tf · idf scores that measure the relevance of the newswire article sentences to the given topic. It also measures the similarity between candidate sentences and the previous articles already read by the user. NESS ranked well in the competition, obtaining excellent scores in linguistic quality and overall responsiveness. 1