Event-Driven Headline Generation

We propose an event-driven model for headline generation. Given an input document, the system identifies a key event chain by extracting a set of structural events that describe them. Then a novel multi-sentence compression algorithm is used to fuse the extracted events, generating a headline for the document. Our model can be viewed as a novel ion of extractive and abstractive headline generation, combining the advantages of both methods using event structures. Standard evaluation shows that our model achieves the best performance compared with previous state-of-the-art systems.

• Type: Journal
• Year: 2015
• Where: ACL
• Authors: Rui Sun, Yue Zhang, Meishan Zhang, Dong-Hong Ji
• Keywords: ACL 2015, Computational Linguistics