Research Area:  Machine Learning
Arabic keyphrase extraction is a crucial task due to the significant and growing amount of Arabic text on the web generated by a huge population. It is becoming a challenge for the community of Arabic natural language processing because of the severe shortage of resources and published processing systems. In this paper we propose a deep learning based approach for Arabic keyphrase extraction that achieves better performance compared to the related competitive approaches. We also introduce the community with an annotated large-scale dataset of about 6000 scientific abstracts which can be used for training, validating and evaluating deep learning approaches for Arabic keyphrase extraction.
Keywords:  
Arabic natural language processing
Keyphrase Extraction
Machine Learning
Deep Learning
Author(s) Name:  Muhammad Helmy, R.M. Vigneshram, Giuseppe Serra, Carlo Tasso
Journal name:  Procedia Computer Science
Conferrence name:  
Publisher name:  Elsevier
DOI:  10.1016/j.procs.2018.10.486
Volume Information:  Volume 142, 2018, Pages 254-261
Paper Link:   https://www.sciencedirect.com/science/article/pii/S1877050918321902