A noisy-channel model for document compression

TitleA noisy-channel model for document compression
Publication TypeConference Papers
Year of Publication2002
AuthorsDaumé H, Marcu D
Conference NameProceedings of the 40th Annual Meeting on Association for Computational Linguistics
Date Published2002///
PublisherAssociation for Computational Linguistics
Conference LocationStroudsburg, PA, USA

We present a document compression system that uses a hierarchical noisy-channel model of text production. Our compression system first automatically derives the syntactic structure of each sentence and the overall discourse structure of the text given as input. The system then uses a statistical hierarchical model of text production in order to drop non-important syntactic and discourse constituents so as to generate coherent, grammatical document compressions of arbitrary length. The system outperforms both a baseline and a sentence-based compression system that operates by simplifying sequentially all sentences in a text. Our results support the claim that discourse knowledge plays an important role in document summarization.