{
  "id": 116092,
  "title": "missing data in annotations?",
  "url": "/competitions/tensorflow2-question-answering/discussion/116092",
  "author_name": "",
  "post_date": "2019-11-07T03:04:08.471348Z",
  "votes": 3,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Seems about half the training data have long_answer_start and long_answer_end in annotations as -1.\nthis means there is no long answer?\nIs this correct or am i missing something?</p>",
  "messages": [
    {
      "id": "667263",
      "postDate": "11/07/2019 03:04:08",
      "content": "<p>Seems about half the training data have long_answer_start and long_answer_end in annotations as -1.\nthis means there is no long answer?\nIs this correct or am i missing something?</p>",
      "rawMarkdown": "Seems about half the training data have long_answer_start and long_answer_end in annotations as -1.\nthis means there is no long answer?\nIs this correct or am i missing something?",
      "votes": null
    },
    {
      "id": "667278",
      "postDate": "11/07/2019 03:56:20",
      "content": "<p>This is an excerpt from the paper describing the dataset (<a href=\"https://ai.google/research/pubs/pub47761.pdf\">https://ai.google/research/pubs/pub47761.pdf</a>):</p>\n\n<blockquote>\n  <p>In total, annotators identify a long answer for 49% of the examples, and short answer spans or a yes/no answer for 36% of the examples. We consider the choice of whether or not to answer a question a core part of the question answering task, and do not discard the remaining 51% that have no answer labeled.</p>\n</blockquote>",
      "rawMarkdown": "This is an excerpt from the paper describing the dataset (https://ai.google/research/pubs/pub47761.pdf):\n&gt; In total, annotators identify a long answer for 49% of the examples, and short answer spans or a yes/no answer for 36% of the examples. We consider the choice of whether or not to answer a question a core part of the question answering task, and do not discard the remaining 51% that have no answer labeled.",
      "votes": null
    },
    {
      "id": "674714",
      "postDate": "11/17/2019 00:17:20",
      "content": "<p>but if we submit the origin submission file which has an empty PredictionString, you will find that the score is 0; So it's the limitation of the games?</p>",
      "rawMarkdown": "but if we submit the origin submission file which has an empty PredictionString, you will find that the score is 0; So it's the limitation of the games?",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 667278,
      "author_name": "thedrcat",
      "author_url": "",
      "post_date": "11/07/2019 03:56:20",
      "content": "<p>This is an excerpt from the paper describing the dataset (<a href=\"https://ai.google/research/pubs/pub47761.pdf\">https://ai.google/research/pubs/pub47761.pdf</a>):</p>\n\n<blockquote>\n  <p>In total, annotators identify a long answer for 49% of the examples, and short answer spans or a yes/no answer for 36% of the examples. We consider the choice of whether or not to answer a question a core part of the question answering task, and do not discard the remaining 51% that have no answer labeled.</p>\n</blockquote>",
      "votes": null,
      "replies": []
    },
    {
      "id": 674714,
      "author_name": "wanderingz",
      "author_url": "",
      "post_date": "11/17/2019 00:17:20",
      "content": "<p>but if we submit the origin submission file which has an empty PredictionString, you will find that the score is 0; So it's the limitation of the games?</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "667263": "Seems about half the training data have long_answer_start and long_answer_end in annotations as -1.\nthis means there is no long answer?\nIs this correct or am i missing something?",
    "667278": "This is an excerpt from the paper describing the dataset (https://ai.google/research/pubs/pub47761.pdf):\n&gt; In total, annotators identify a long answer for 49% of the examples, and short answer spans or a yes/no answer for 36% of the examples. We consider the choice of whether or not to answer a question a core part of the question answering task, and do not discard the remaining 51% that have no answer labeled.",
    "674714": "but if we submit the origin submission file which has an empty PredictionString, you will find that the score is 0; So it's the limitation of the games?"
  },
  "source": "meta"
}