{
  "id": 5612,
  "title": "Making a noncompetitive submissionout of curiosity",
  "url": "/competitions/facebook-recruiting-iii-keyword-extraction/discussion/5612",
  "author_name": "",
  "post_date": "2013-09-01T09:11:12.187Z",
  "votes": null,
  "comment_count": 5,
  "views": 2486,
  "content": "<p>I work at Stack Exchange. About a year ago, we held a very similar contest internally. While that contest was not restricted to only using title and body of a question, my (winning) solution did in fact only use these two features.</p>\n<p>I would like to make a submission using this algorithm; not because I have ambitions to win this contest, but just out of curiosity how it compares to other solutions.</p>\n<p>I would assume that this is okay except for one rule which I'm not sure about how to interpret it in this context:</p>\n<p style=\"padding-left: 30px\"><span style=\"line-height: 1.4\">No sharing outside teams</span></p>\n<p style=\"padding-left: 30px\">Any sharing code or data outside of teams is not permitted. This includes making code or data made available to all players, such as on the forums.</p>\n<p>While my solution is not public, and while I worked on it on my own, it is of course accessible internally to my coworkers.</p>\n<p>Is it acceptable for me to make a submission under these circumstances?</p>",
  "messages": [
    {
      "id": "29909",
      "postDate": "09/01/2013 09:11:12",
      "content": "<p>I work at Stack Exchange. About a year ago, we held a very similar contest internally. While that contest was not restricted to only using title and body of a question, my (winning) solution did in fact only use these two features.</p>\n<p>I would like to make a submission using this algorithm; not because I have ambitions to win this contest, but just out of curiosity how it compares to other solutions.</p>\n<p>I would assume that this is okay except for one rule which I'm not sure about how to interpret it in this context:</p>\n<p style=\"padding-left: 30px\"><span style=\"line-height: 1.4\">No sharing outside teams</span></p>\n<p style=\"padding-left: 30px\">Any sharing code or data outside of teams is not permitted. This includes making code or data made available to all players, such as on the forums.</p>\n<p>While my solution is not public, and while I worked on it on my own, it is of course accessible internally to my coworkers.</p>\n<p>Is it acceptable for me to make a submission under these circumstances?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "29963",
      "postDate": "09/01/2013 23:19:03",
      "content": "<p>Curious about the F1 scores of your models . You must try dozens of models, right?Same evaluation , F1?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "29981",
      "postDate": "09/02/2013 08:08:33",
      "content": "<p>We didn't use F1 in our internal competition; our evaluation function had to be per-question, not per-tag. We also didn't punish false positives: We predicted five tags per question no matter what. So my model has to be slightly modified to adjust to this, but that's a minimal change.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "30040",
      "postDate": "09/03/2013 08:17:35",
      "content": "<p>I have made the submission now. If this is not acceptable after all, feel free to remove it; my curiosity is satisfied.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "30053",
      "postDate": "09/03/2013 14:22:27",
      "content": "<p>Hi balpha,</p>\n<p>This is fine, as long as you are not using any information unavailable to other competitors.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "30058",
      "postDate": "09/03/2013 14:50:24",
      "content": "<p>Okay, thanks. All I'm using is the provided dataset and a Porter2 stemmer.</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 29963,
      "author_name": "",
      "author_url": "",
      "post_date": "09/01/2013 23:19:03",
      "content": "<p>Curious about the F1 scores of your models . You must try dozens of models, right?Same evaluation , F1?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 29981,
      "author_name": "balpha",
      "author_url": "",
      "post_date": "09/02/2013 08:08:33",
      "content": "<p>We didn't use F1 in our internal competition; our evaluation function had to be per-question, not per-tag. We also didn't punish false positives: We predicted five tags per question no matter what. So my model has to be slightly modified to adjust to this, but that's a minimal change.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 30040,
      "author_name": "balpha",
      "author_url": "",
      "post_date": "09/03/2013 08:17:35",
      "content": "<p>I have made the submission now. If this is not acceptable after all, feel free to remove it; my curiosity is satisfied.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 30053,
      "author_name": "wcukierski",
      "author_url": "",
      "post_date": "09/03/2013 14:22:27",
      "content": "<p>Hi balpha,</p>\n<p>This is fine, as long as you are not using any information unavailable to other competitors.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 30058,
      "author_name": "balpha",
      "author_url": "",
      "post_date": "09/03/2013 14:50:24",
      "content": "<p>Okay, thanks. All I'm using is the provided dataset and a Porter2 stemmer.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "29909": "",
    "29963": "",
    "29981": "",
    "30040": "",
    "30053": "",
    "30058": ""
  },
  "source": "meta"
}