ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images
This addresses the problem of limited OCR-VQA resources for Vietnamese, an incremental contribution by adapting existing methods to a new language-specific dataset.
The authors tackled the lack of datasets for Optical Character Recognition-Visual Question Answering (OCR-VQA) in low-resource languages by introducing ViOCRVQA, a Vietnamese dataset with 28,000+ images and 120,000+ question-answer pairs, and proposed VisionReader, which achieved 0.4116 EM and 0.6990 F1-score on the test set.
Optical Character Recognition - Visual Question Answering (OCR-VQA) is the task of answering text information contained in images that have just been significantly developed in the English language in recent years. However, there are limited studies of this task in low-resource languages such as Vietnamese. To this end, we introduce a novel dataset, ViOCRVQA (Vietnamese Optical Character Recognition - Visual Question Answering dataset), consisting of 28,000+ images and 120,000+ question-answer pairs. In this dataset, all the images contain text and questions about the information relevant to the text in the images. We deploy ideas from state-of-the-art methods proposed for English to conduct experiments on our dataset, revealing the challenges and difficulties inherent in a Vietnamese dataset. Furthermore, we introduce a novel approach, called VisionReader, which achieved 0.4116 in EM and 0.6990 in the F1-score on the test set. Through the results, we found that the OCR system plays a very important role in VQA models on the ViOCRVQA dataset. In addition, the objects in the image also play a role in improving model performance. We open access to our dataset at link (https://github.com/qhnhynmm/ViOCRVQA.git) for further research in OCR-VQA task in Vietnamese.