Automatic Headline Generation using Character Cross-Correlation

Fahad Alotaiby
King Saud University


Abstract

Arabic language is a morphologically complex language. Affixes and clitics are regularly attached to stems which make direct comparison between words not practical. In this paper we propose a new automatic headline generation technique that utilizes character cross-correlation to extract best headlines and to overcome the Arabic language complex morphology. The systems that uses character cross-correlation achieves ROUGE-L score of 0.19384 while the exact word matching scores only 0.17252 for the same set of documents.




Full paper: http://www.aclweb.org/anthology/P/P11/.pdf