Paper: Sentence Compression as a Step in Summarization or an Alternative Path in Text Shortening

ACL ID C08-2035
Title Sentence Compression as a Step in Summarization or an Alternative Path in Text Shortening
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2008
Authors

The originality of this work leads in tack- ling text compression using an unsuper- vised method, based on a deep linguistic analysis, and without resorting on a learn- ing corpus. This work presents a system for dependent tree pruning, while preserv- ing the syntactic coherence and the main informational contents, and led to an op- erational software, named COLIN. Exper- iment results show that our compressions get honorable satisfaction levels, with a mean compression ratio of 38 %.