Using machine learning to generate headlines

In this paper, we present a system which generates headlines for a text. Our system, the HybridTrim system, uses a linguistic, statistical and positional information in combination with a machine learning technique to identify topic labels for headlines in a text. In this paper, we compare our system with the Topiary system which, in contrast, uses a statistical learning approach to finding topic descriptors for headlines. Both systems combine these topic descriptors with a compressed version of the lead sentence. The performance of these systems is evaluated using the ROUGE evaluation suite on the DUC 2004 news stories collection.