Compression entropique de phrases contrôlée par un perceptron

Sentence compression is a necessary component to the generation of abstracts. Previous studies focused mainly on the syntactic tree representation of the sentence. Our approach is a statistic approach, which does not use syntactic trees, which can be inaccurate in sentence analysis. At the core of our system is a language model based on lemma bigrams and part-of-speech tags (only a shallow parsing is performed) as well as an entropy computation over sentences to retrieve the best-compressed sentences. We also introduce the perceptron which is used to classify the compressed and non-compressed sentences and to indicate whether or not a sentence should be compressed.