Sentence compression with a Markov logic network

A method was developed to compress English sentences by removing unimportant words.The Markov logic network(MLN) incorporates local linguistic features and captures global dependencies between word deletion operations.The MLN based method combines the advantages of discriminative learning and integer linear programming by incorporating a rich set of features and expressing global constraints as logic formulae.Tests on both written and spoken news corpora show that this approach is superior to state-of-the-art methods.For similar compression rates,this method achieves a much higher F-score of dependency relations in comparison with human compressions.