Generating Image Captions in Arabic Using Root-Word Based Recurrent Neural Networks and Deep Neural Networks

2018-02-08

Proceedings of the AAAI Conference on Artificial Intelligence, 32

Volume

Thirty-Second AAAI Conference on Artificial Intelligence 2018

Student Abstract Track

Automatic caption generation of an image requires both computer vision and natural language processing techniques. Despite of advanced research in English caption generation, research on generating Arabic descriptions of an image is extremely limited. Semitic languages like Arabic are heavily influenced by root-words. We leverage this critical dependency of Arabic and in this paper are the first to generate captions of an image directly in Arabic using root-word based Recurrent Neural Networks and Deep Neural Networks. We report the first BLEU score for direct Arabic caption generation. Experimental results confirm that generating image captions using root-words directly in Arabic significantly outperforms the English-Arabic translated captions using state-of-the-art methods.

10.1609/aaai.v32i1.12179