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
