Generative image captioning in Urdu using deep learning

Abstract Urdu is morphologically rich language and lacks the resources available in English. While several studies on image captioning task English have been published, this among pioneer generative captioning. The study makes key contributions: (i) it presents a new dataset for captioning, (ii) different attention-based architectures language. These attention mechanisms are to language, as those never used (iii) Finally, performs quantitative qualitative analysis of results by studying impact model Urdu’s caption generation task. extensive experiments show encouraging such BLEU-1 score 72.5, BLEU-2 56.9, BLEU-3 42.8, BLEU-4 31.6. we present data code future research via GitHub ( https://github.com/saeedhas/Urdu_cap_gen ).