Automatic headline generation using character cross-correlation

Authors:
Fahad A. Alotaiby
Affiliations:
King Saud University, Riyadh, Saudi Arabia
Venue:
HLT-SS '11 Proceedings of the ACL 2011 Student Session
Year:
2011

Citing 5
Cited 0

Using leading text for news summaries: evaluation results and implications for commercial summarization applications

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
A new probabilistic model for title generation

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Hedge Trimmer: a parse-and-trim approach to headline generation

HLT-NAACL-DUC '03 Proceedings of the HLT-NAACL 03 on Text summarization workshop - Volume 5
Issues in Arabic orthography and morphology analysis

Semitic '04 Proceedings of the Workshop on Computational Approaches to Arabic Script-based Languages

Quantified Score

Hi-index	0.00

Visualization

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 system 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.