{
  "id": 72544,
  "title": "Does off-the-shelf tokenizers violate the external data limit?",
  "url": "/competitions/quora-insincere-questions-classification/discussion/72544",
  "author_name": "",
  "post_date": "2018-11-24T09:29:02.369336200Z",
  "votes": null,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Some pre-installed packages (e.g., spacy) have modules like lemmatizer, tokenizer, etc.\nHowever, these off-the-shelf modules could be pre-trained on the \"external\" data.\nAre we allowed to use these modules?</p>",
  "messages": [
    {
      "id": "426975",
      "postDate": "11/24/2018 09:29:02",
      "content": "<p>Some pre-installed packages (e.g., spacy) have modules like lemmatizer, tokenizer, etc.\nHowever, these off-the-shelf modules could be pre-trained on the \"external\" data.\nAre we allowed to use these modules?</p>",
      "rawMarkdown": "Some pre-installed packages (e.g., spacy) have modules like lemmatizer, tokenizer, etc.\nHowever, these off-the-shelf modules could be pre-trained on the \"external\" data.\nAre we allowed to use these modules?",
      "votes": null
    },
    {
      "id": "427006",
      "postDate": "11/24/2018 10:34:07",
      "content": "<p>According to <a href=\"https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/70715#latest-426826\">https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/70715#latest-426826</a> we can use all packages that are installed within the docker image.</p>",
      "rawMarkdown": "According to https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/70715#latest-426826 we can use all packages that are installed within the docker image.",
      "votes": null
    },
    {
      "id": "427007",
      "postDate": "11/24/2018 10:35:14",
      "content": "<p>You can use them, I've used (and still use) some of them and haven't had any problem submitting.</p>",
      "rawMarkdown": "You can use them, I've used (and still use) some of them and haven't had any problem submitting.",
      "votes": null
    },
    {
      "id": "427061",
      "postDate": "11/24/2018 13:19:17",
      "content": "<p>I should read such a thread carefully...\nThanks!</p>",
      "rawMarkdown": "I should read such a thread carefully...\nThanks!",
      "votes": null
    },
    {
      "id": "428277",
      "postDate": "11/27/2018 02:27:30",
      "content": "<p>Now that the matter is settled, maybe you can put my kernel here to good use? <a href=\"https://www.kaggle.com/jpmiller/bonus-vectors-with-spacy/\">https://www.kaggle.com/jpmiller/bonus-vectors-with-spacy/</a></p>",
      "rawMarkdown": "Now that the matter is settled, maybe you can put my kernel here to good use? https://www.kaggle.com/jpmiller/bonus-vectors-with-spacy/",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 427006,
      "author_name": "philippsinger",
      "author_url": "",
      "post_date": "11/24/2018 10:34:07",
      "content": "<p>According to <a href=\"https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/70715#latest-426826\">https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/70715#latest-426826</a> we can use all packages that are installed within the docker image.</p>",
      "votes": null,
      "replies": [
        {
          "id": 427061,
          "author_name": "yufuin",
          "author_url": "",
          "post_date": "11/24/2018 13:19:17",
          "content": "<p>I should read such a thread carefully...\nThanks!</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 427007,
      "author_name": "theoviel",
      "author_url": "",
      "post_date": "11/24/2018 10:35:14",
      "content": "<p>You can use them, I've used (and still use) some of them and haven't had any problem submitting.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 428277,
      "author_name": "jpmiller",
      "author_url": "",
      "post_date": "11/27/2018 02:27:30",
      "content": "<p>Now that the matter is settled, maybe you can put my kernel here to good use? <a href=\"https://www.kaggle.com/jpmiller/bonus-vectors-with-spacy/\">https://www.kaggle.com/jpmiller/bonus-vectors-with-spacy/</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "426975": "Some pre-installed packages (e.g., spacy) have modules like lemmatizer, tokenizer, etc.\nHowever, these off-the-shelf modules could be pre-trained on the \"external\" data.\nAre we allowed to use these modules?",
    "427006": "According to https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/70715#latest-426826 we can use all packages that are installed within the docker image.",
    "427007": "You can use them, I've used (and still use) some of them and haven't had any problem submitting.",
    "427061": "I should read such a thread carefully...\nThanks!",
    "428277": "Now that the matter is settled, maybe you can put my kernel here to good use? https://www.kaggle.com/jpmiller/bonus-vectors-with-spacy/"
  },
  "source": "meta"
}