{
  "fetched_at": "2026-10-19T13:25:18Z",
  "source_url": "https://www.kaggle.com/competitions/faa-2020-cognate-identification/data",
  "pages": [
    {
      "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 - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>IE2012-lexical-data.train.csv</strong> - the training dataset</li>\n<li><strong>IE2013-lexical-data.test.csv</strong> - the test dataset</li>\n<li><strong>IE2012-test-maj-baseline.csv</strong> - a sample submission that implements the majority baseline (i.e., the 0 class for all examples)</li>\n</ul>\n\n<h2>Data fields</h2>\n<ul>\n<li><strong>Id</strong> - id unique for pair of words (i.e., the cognate candidates)</li>\n<li><strong>Category</strong> - Class label (0 or 1) indicating whether the 2 words are cognates or not, respectively)</li>\n<li><strong>word1</strong> - string or phonetic representation of the first word </li>\n<li><strong>language1</strong> - language of the first word</li>\n<li><strong>word2</strong> - string or phonetic representation of the second word </li>\n<li><strong>language2</strong> - language of the second word</li>\n<li><strong>meaning</strong> - concept or meaning associated with the two words</li>\n<li><strong>Usage</strong> - field to be ignored</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Welcome to the Cognate Identification competition organized as part of the FAA course (year 2019-2020), UdL, FIL, Master Informatique</h2>\n\nThis competition is about predicting whether two word forms (or phonetic realizations of these words) that share the same meaning in two different languages are historically related (in the sense that they come from the same ancestor word). Two words that are historically related are called cognates. For instance, the English \"father\" and French \"père\" words are cognates, both derived from Latin \"pater\", whereas Latin \"deus\" and Greek \"theos\", despite their apparent sound similarity, are not cognates as they come from different roots.\n\nFrom a Machine Learning point of view, we are dealing with binary classification problem, having to decide whether two words are cognates (positive class) or not (negative class). The dataset used for this competition contains around 1.4M word pairs, corresponding to 209 original meanings/concepts realized in over 150 languages. This dataset is split into 1.14M training examples (80%) and .29M test examples (20%).  \n\n\n<h2>Acknowledgements</h2>\n\nThis dataset was extracted from the Indo-European Lexical Cognacy Database (IELex), collected at the Max Planck Institute in the Netherlands: http://ielex.mpi.nl/.\n\n<h2>Competition manager</h2>\n\nFor any information regarding this competition, please contact Pascal Denis (at inria.fr)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is classification accuracy, which is computed as follows:</p>\n<p>\\[ Acc = 1-Err_{test} = 1-\\frac{1}{n_{test}}\\sum_{i=1}^{n_{test}} |f_{\\theta}(\\textbf{x}_i)-y_i| \\]</p>\n<p>where: \\\\((\\textbf{x}_i,y_i)\\\\) is a test example, \\\\(n_{test}\\\\) is the total number of test examples, and \\\\(f_{\\theta}\\\\) is the prediction function you have learned.</p>\n\n<h2>Submission Format</h2>\n<p><strong>For every team in the competition</strong>, submission files should contain exactly two columns: Id and Category. Id is a unique ID per datapoint, while Category indicates whether the example is an instance of cognates (value: 1) or not (value: 0). For example:</p>\n<pre>Id,Category<br>540102,0<br></pre>\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}