Modelling Compression with Discourse Constraints

Sentence compression holds promise for many applications ranging from summarisation to subtitle generation and subtitle generation. The task is typically performed on isolated sentences without taking the surrounding context into account, even though most applications would operate over entire documents. In this paper we present a discourse informed model which is capable of producing document compressions that are coherent and informative. Our model is inspired by theories of local coherence and formulated within the framework of Integer Linear Programming. Experimental results show significant improvements over a stateof-the-art discourse agnostic approach.

• Type: Conference
• Year: 2007
• Where: EMNLP
• Authors: James Clarke, Mirella Lapata
• Keywords: Compression Holds Promise, Discourse Informed Model, EMNLP 2007, Natural Language Processing, Subtitle Generation