Violet: A Vision-Language Model for Arabic Image Captioning with Gemini Decoder
Document Type
Conference Proceeding
Publication Title
ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Proceedings
Abstract
Although image captioning has a vast array of applications, it has not reached its full potential in languages other than English. Arabic, for instance, although the native language of more than 400 million people, remains largely underrepresented in this area. This is due to the lack of labeled data and powerful Arabic generative models. We alleviate this issue by presenting a novel vision-language model dedicated to Arabic, dubbed Violet. Our model is based on a vision encoder and a Gemini text decoder that maintains generation fluency while allowing fusion between the vision and language components. To train our model, we introduce a new method for automatically acquiring data from available English datasets. We also manually prepare a new dataset for evaluation. Violet performs sizeably better than our baselines on all of our evaluation datasets. For example, it reaches a CIDEr score of 61.2 on our manually annotated dataset and achieves an improvement of 13 points on Flickr8k.
First Page
1
Last Page
11
Publication Date
1-1-2023
Recommended Citation
A. Mohamed et al., "Violet: A Vision-Language Model for Arabic Image Captioning with Gemini Decoder," ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Proceedings, pp. 1 - 11, Jan 2023.