We present a novel unsupervised method for sentence compression which relies on a Stanford Typed Dependencies to extract information items, then generates compressed sentences via Natural Language Generation(NLG) engine. An automatic evaluation shows that our method obtains better results. We demonstrate that the choice of the parser affects the performance of the system. © 2011 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Li, P., & Wang, Y. (2011). Sentence compression with natural language generation. In Advances in Intelligent and Soft Computing (Vol. 123, pp. 357–363). https://doi.org/10.1007/978-3-642-25661-5_46
Mendeley helps you to discover research relevant for your work.