{
  "fetched_at": "2026-10-19T13:32:04Z",
  "source_url": "https://www.kaggle.com/competitions/efreiparisdeeplearning2019/data",
  "pages": [
    {
      "name": "rules",
      "content": "<h3>One account per participant</h3>\n<p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n<h3>No private sharing outside teams</h3>\n<p>Privately sharing code or data outside of teams is not permitted.</p>\n\n<h3>Team Mergers</h3>\n<p>Team mergers are not allowed in this competition.</p>\n\n<h3>Team Limits</h3>\n<p>The maximum team size is 3 students.</p>\n<h3>Submission Limits</h3>\n<p>You may submit a maximum of 5 entries per day.</p>\n<p>You may select up to 2 final submissions for judging.</p>\n<h3>Competition Timeline</h3>\n<p>Start Date: <strong>11/27/2019 12:00 AM UTC</strong></p>\n<p>End Date: <strong>12/28/2019 11:59 PM UTC</strong></p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>Files descriptions</h2>\n<ul>\n<li><strong>dataset_train.csv</strong> - CSV file containing the 392 663 training samples with their labels</li>\n<li><strong>dataset_test_no_labels.csv</strong> - CSV file containing the 19 648 test samples</li>\n<li><strong>example_submission_test.csv</strong> - a dummy submission test CSV in the correct format as example</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>index</strong> - sample id to be classified</li>\n<li><strong>sentence_1</strong> - first sentence of the pair</li>\n<li><strong>sentence_2</strong> - second sentence of the pair</li>\n<li><strong>label</strong> - category to predict among 3 possible classes</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h1>EFREI Paris - Deep Learning Challenge - 2019</h1>\n\n<p>In this challenge you will be building a model that automatically determines logical entailment between two sentences.</p>\n<p>You are free to handle the data as you wish, though your final submission file must be reproductible using solely your model.<p>\n<p>The size of the dataset is acceptable enough to be processed correctly by your personal computer. That being said, it could be helpful to profit from free cloud computing services, like Kaggle kernels or Google Colab.</p>\n<p>Any cheating strategies, like manually labelling the test dataset, would lead to a disqualification and a minimal final grade.</p>\nRemember that final evaluation will be based on ranking, quality of code and ideas.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2>Goal</h2>\n<p>The goal of this InClass competition is to predict the right logical entailment for each sentences couple. Note that the dataset is clearly balanced between all the classes. For every index in the test set, you should predict the correct label, which can only take one of the following three values: contradiction, neutral or entailment.</p>\n<h2>Metric</h2>\n<p>Since the dataset is balanced, this competition is evaluated on the categorization accuracy of your predictions (the percentage of logical entailments you get correct).</p>\n<h2>Submission Format</h2>\n<p>For each index in the test set, you must predict a label.</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>index,label<br />0,contradiction<br /><span style=\"font-size: 14px; line-height: 1.4em;\">1,neutral<br />2,entailment<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">3,contradiction<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}