Abstract
This research belongs to the Natural Language Processing field and more specifically focuses on text summarization.<br />The originality of this thesis leads in tackling a type of summarization that has not been studied much, text compression using an unsupervised method.<br />This work presents an interactive and incremental system for syntagmatic tree pruning, while preserving the syntactic coherence and the main informational contents.<br />On the theoretical side, this work is based on the Government and Biding theory of Noam Chomsky and more precisely on the formal representation of the X-bar theory, to aims at a strong foundation for a computational model compatible with syntactic compression of sentences.<br />This work led to an operational software, named COLIN, which proposes two modalities: an automated compression and an assistance to summarization in a semi-automated form, directed through a tight interaction with the user.<br />This software has been evaluated thanks to a quite complex protocol using 25 volunteers.<br />Experiment results show that 1) the notion of reference abstract which is the basic of classical evaluation is at least questionable, 2) semi-automated compression has been given a high value by users 3) fully automated compressions also get honourable satisfaction levels.<br />With a compression ratio of over 40% for all genres of text, COLIN offers an appreciable support as an assistance to text compression, without resorting on a learning corpus, and with a user-friendly interface.