An extractive supervised two-stage method for sentence compression

We present a new method that compresses sentences by removing words. In a first stage, it generates candidate compressions by removing branches from the source sentence's dependency tree using a Maximum Entropy classifier. In a second stage, it chooses the best among the candidate compressions using a Support Vector Machine Regression model. Experimental results show that our method achieves state-of-the-art performance without requiring any manually written rules.

• Type: Journal
• Year: 2010
• Where: NAACL
• Authors: Dimitrios Galanis, Ion Androutsopoulos
• Keywords: Candidate Compressions, Computational Linguistics, Maximum Entropy Classifier, NAACL 2010, Vector Machine Regression