{
  "fetched_at": "2026-10-20T06:52:34Z",
  "source_url": "https://www.kaggle.com/competitions/ViTextVQA-F1-evaluation/data",
  "pages": [
    {
      "name": "data-description",
      "content": "ViTextVQA contains over 16,000 images and over 50,000 questions with answers. The dataset is designed to evaluate the ability of AI models to comprehend text within images and answer questions based on that understanding.\nThe purpose of ViTextVQA is to provide a benchmark for evaluating the reading comprehension ability of Visual Question Answering (VQA) models in the Vietnamese language. As a developing country, Vietnam is still in need of resources and benchmarks to advance research in AI and machine learning.\n\nplease contact 21521333@gm.uit.edu.vn or haryquan.minh@gmail.com for providing dataset",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "**Measuring System Performance in Question-Answering Tasks Using F1-Score**\n\nF1-score is a widely used metric for evaluating the performance of a system in question-answering tasks. This metric assesses how well the system's answers match the correct ones. It combines two important aspects: precision and recall. Precision measures the accuracy of the system's answers, while recall evaluates how many correct answers the system can identify. By combining these two, F1-score provides a comprehensive evaluation of the system's ability to deliver accurate and complete answers.\n\nThe formulas for Precision, Recall, and F1 Score are as follows:\n\n$$\n\\textbf{Precision} = \\frac{\\text{Count of tokens predicted exactly}}{\\text{Count of tokens predicted}}\n$$\n\n$$\n\\textbf{Recall} = \\frac{\\text{Count of tokens predicted exactly}}{\\text{Count of gold standard tokens}}\n$$\n\n$$\n\\textbf{F1-score} = \\frac{2 \\times \\text{Precision} \\times \\text{Recall}}{\\text{Precision} + \\text{Recall}}\n$$\n\nThe purpose of these metrics is to evaluate how good a system is at providing accurate and complete answers.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "\n## Submission File\nFor each ID in the test set, you must predict a answer for the question. The file should contain a header and have the following format:\n\n```\nID,Answer\n2,tôi yêu bạn\n5,anh yêu em\n6,i love you\netc.\n```\n\nParticipants are required to submit predictions for both the development (dev) set and the test set. The results for the dev set will be used for public leaderboard rankings, while the results for the test set will be used for private leaderboard rankings. The dev set results are evaluated and ranked before the test set results.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Maintain integrity and honesty in your work.\n - Give your best effort and stay dedicated.\n - Enjoy the challenge and have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "dataset is the first high-quality large-scale dataset in Vietnamese specializing in understanding text appearing in images.\n\nThis is the dedicated portal for submitting and evaluating the F1-Scores of your models. Here, you can test your model’s performance on our dataset and see how it compares to other models in the community.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}