{
  "id": 247515,
  "title": "What is it we are predicting?",
  "url": "/competitions/coleridgeinitiative-show-us-the-data/discussion/247515",
  "author_name": "",
  "post_date": "2021-06-19T23:55:20.034637800Z",
  "votes": null,
  "comment_count": 3,
  "views": 0,
  "content": "<p>I know Im a bit late to this competition and forgive me for asking a dumb question, but can someone please explain what we are supposed to do here in a manner more clearly that what the competition host has explained it?  What exactly are we \"predicting\" in the competition?  From what I can understand it is just an automated way to identify the sources each article is citing?  How exactly are we using NLP to do any sort of predicting?</p>",
  "messages": [
    {
      "id": "1357772",
      "postDate": "06/19/2021 23:55:20",
      "content": "<p>I know Im a bit late to this competition and forgive me for asking a dumb question, but can someone please explain what we are supposed to do here in a manner more clearly that what the competition host has explained it?  What exactly are we \"predicting\" in the competition?  From what I can understand it is just an automated way to identify the sources each article is citing?  How exactly are we using NLP to do any sort of predicting?</p>",
      "rawMarkdown": "I know Im a bit late to this competition and forgive me for asking a dumb question, but can someone please explain what we are supposed to do here in a manner more clearly that what the competition host has explained it?  What exactly are we \"predicting\" in the competition?  From what I can understand it is just an automated way to identify the sources each article is citing?  How exactly are we using NLP to do any sort of predicting?",
      "votes": null
    },
    {
      "id": "1358875",
      "postDate": "06/20/2021 21:01:55",
      "content": "<p>the data set names mentioned in the texts</p>",
      "rawMarkdown": "the data set names mentioned in the texts",
      "votes": null
    },
    {
      "id": "1359003",
      "postDate": "06/21/2021 02:06:36",
      "content": "<p>It's not completely accurate.<br>\nWhat we should predict is the semantic context within which a dataset has been called out.<br>\nSome of the dataset names in the publications are not mentioned, so if we predict these, they might be counted as FP.</p>\n<p><a href=\"https://www.kaggle.com/c/coleridgeinitiative-show-us-the-data/discussion/228337#1253196\" target=\"_blank\">https://www.kaggle.com/c/coleridgeinitiative-show-us-the-data/discussion/228337#1253196</a></p>\n<pre><code>This is a great explanation, @julialane. The task is to identify the semantic context of a dataset's mentions. The test data contains a very large number of datasets, contexts, and publications that are entirely unseen in the training set. A model will need to generalize to the task to do well.\n@sirishks - I will be answering your follow-up questions in your thread.\n</code></pre>",
      "rawMarkdown": "It's not completely accurate.\nWhat we should predict is the semantic context within which a dataset has been called out.\nSome of the dataset names in the publications are not mentioned, so if we predict these, they might be counted as FP.\n\nhttps://www.kaggle.com/c/coleridgeinitiative-show-us-the-data/discussion/228337#1253196\n\n```\nThis is a great explanation, @julialane. The task is to identify the semantic context of a dataset's mentions. The test data contains a very large number of datasets, contexts, and publications that are entirely unseen in the training set. A model will need to generalize to the task to do well.\n@sirishks - I will be answering your follow-up questions in your thread.\n```",
      "votes": null
    },
    {
      "id": "1360205",
      "postDate": "06/21/2021 22:43:17",
      "content": "<p>なるほど         </p>",
      "rawMarkdown": "なるほど",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1358875,
      "author_name": "aegehbi",
      "author_url": "",
      "post_date": "06/20/2021 21:01:55",
      "content": "<p>the data set names mentioned in the texts</p>",
      "votes": null,
      "replies": [
        {
          "id": 1359003,
          "author_name": "spshota",
          "author_url": "",
          "post_date": "06/21/2021 02:06:36",
          "content": "<p>It's not completely accurate.<br>\nWhat we should predict is the semantic context within which a dataset has been called out.<br>\nSome of the dataset names in the publications are not mentioned, so if we predict these, they might be counted as FP.</p>\n<p><a href=\"https://www.kaggle.com/c/coleridgeinitiative-show-us-the-data/discussion/228337#1253196\" target=\"_blank\">https://www.kaggle.com/c/coleridgeinitiative-show-us-the-data/discussion/228337#1253196</a></p>\n<pre><code>This is a great explanation, @julialane. The task is to identify the semantic context of a dataset's mentions. The test data contains a very large number of datasets, contexts, and publications that are entirely unseen in the training set. A model will need to generalize to the task to do well.\n@sirishks - I will be answering your follow-up questions in your thread.\n</code></pre>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1360205,
          "author_name": "aegehbi",
          "author_url": "",
          "post_date": "06/21/2021 22:43:17",
          "content": "<p>なるほど         </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1357772": "I know Im a bit late to this competition and forgive me for asking a dumb question, but can someone please explain what we are supposed to do here in a manner more clearly that what the competition host has explained it?  What exactly are we \"predicting\" in the competition?  From what I can understand it is just an automated way to identify the sources each article is citing?  How exactly are we using NLP to do any sort of predicting?",
    "1358875": "the data set names mentioned in the texts",
    "1359003": "It's not completely accurate.\nWhat we should predict is the semantic context within which a dataset has been called out.\nSome of the dataset names in the publications are not mentioned, so if we predict these, they might be counted as FP.\n\nhttps://www.kaggle.com/c/coleridgeinitiative-show-us-the-data/discussion/228337#1253196\n\n```\nThis is a great explanation, @julialane. The task is to identify the semantic context of a dataset's mentions. The test data contains a very large number of datasets, contexts, and publications that are entirely unseen in the training set. A model will need to generalize to the task to do well.\n@sirishks - I will be answering your follow-up questions in your thread.\n```",
    "1360205": "なるほど"
  },
  "source": "meta"
}