{
  "id": 235089,
  "title": "Entity linking to a knowledge base",
  "url": "/competitions/coleridgeinitiative-show-us-the-data/discussion/235089",
  "author_name": "Mark P",
  "post_date": "2021-04-27T17:27:11.735000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi all</p>\n<p>before I go down a rabbit hole / dead-end I wanted to get your expertise on whether it is worthwhile.</p>\n<p>I have been exploring the use of SciSpacy (first because I wanted a better way of splitting sentences than just on '.' ) and I think it might be useful to use its Entity linker functionality:</p>\n<p>If I test it on the first paper then in this sentence:</p>\n<p><em>This study used data from the National Education Longitudinal Study (NELS:88) to examine the effects of dual enrollment programs for high school students on college degree attainment.</em></p>\n<p>it finds the NELS dataset as an entity which it then links to the knowledge base to show that it is a scientific study:</p>\n<p><strong>Name:  National Education Longitudinal Study\nCUI: C0023981, Name: Longitudinal Studies\nDefinition: Studies in which variables relating to an individual or group of individuals are assessed over a period of time.\nTUI(s): T062\nAliases: (total: 9): \n     Studies, Longitudinal, longitudinal studies, longitudinal study, PROSPECTIVE, long-term study, prospective, Study, Longitudinal, Longitudinal Study, Longitudinal Studies</strong></p>\n<p>My question then is might that information be useful at the very least as a method for identifying  unlabelled datasets in the training data?</p>",
  "messages": [
    {
      "id": 1286206,
      "postDate": "2021-04-27T17:27:11.737Z",
      "content": "<p>Hi all</p>\n<p>before I go down a rabbit hole / dead-end I wanted to get your expertise on whether it is worthwhile.</p>\n<p>I have been exploring the use of SciSpacy (first because I wanted a better way of splitting sentences than just on '.' ) and I think it might be useful to use its Entity linker functionality:</p>\n<p>If I test it on the first paper then in this sentence:</p>\n<p><em>This study used data from the National Education Longitudinal Study (NELS:88) to examine the effects of dual enrollment programs for high school students on college degree attainment.</em></p>\n<p>it finds the NELS dataset as an entity which it then links to the knowledge base to show that it is a scientific study:</p>\n<p><strong>Name:  National Education Longitudinal Study\nCUI: C0023981, Name: Longitudinal Studies\nDefinition: Studies in which variables relating to an individual or group of individuals are assessed over a period of time.\nTUI(s): T062\nAliases: (total: 9): \n     Studies, Longitudinal, longitudinal studies, longitudinal study, PROSPECTIVE, long-term study, prospective, Study, Longitudinal, Longitudinal Study, Longitudinal Studies</strong></p>\n<p>My question then is might that information be useful at the very least as a method for identifying  unlabelled datasets in the training data?</p>",
      "rawMarkdown": "Hi all\n\nbefore I go down a rabbit hole / dead-end I wanted to get your expertise on whether it is worthwhile.\n\nI have been exploring the use of SciSpacy (first because I wanted a better way of splitting sentences than just on '.' ) and I think it might be useful to use its Entity linker functionality:\n\nIf I test it on the first paper then in this sentence:\n\n*This study used data from the National Education Longitudinal Study (NELS:88) to examine the effects of dual enrollment programs for high school students on college degree attainment.*\n\nit finds the NELS dataset as an entity which it then links to the knowledge base to show that it is a scientific study:\n\n\n**Name:  National Education Longitudinal Study\nCUI: C0023981, Name: Longitudinal Studies\nDefinition: Studies in which variables relating to an individual or group of individuals are assessed over a period of time.\nTUI(s): T062\nAliases: (total: 9): \n\t Studies, Longitudinal, longitudinal studies, longitudinal study, PROSPECTIVE, long-term study, prospective, Study, Longitudinal, Longitudinal Study, Longitudinal Studies**\n\nMy question then is might that information be useful at the very least as a method for identifying  unlabelled datasets in the training data?",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1286206": "Hi all\n\nbefore I go down a rabbit hole / dead-end I wanted to get your expertise on whether it is worthwhile.\n\nI have been exploring the use of SciSpacy (first because I wanted a better way of splitting sentences than just on '.' ) and I think it might be useful to use its Entity linker functionality:\n\nIf I test it on the first paper then in this sentence:\n\n*This study used data from the National Education Longitudinal Study (NELS:88) to examine the effects of dual enrollment programs for high school students on college degree attainment.*\n\nit finds the NELS dataset as an entity which it then links to the knowledge base to show that it is a scientific study:\n\n\n**Name:  National Education Longitudinal Study\nCUI: C0023981, Name: Longitudinal Studies\nDefinition: Studies in which variables relating to an individual or group of individuals are assessed over a period of time.\nTUI(s): T062\nAliases: (total: 9): \n\t Studies, Longitudinal, longitudinal studies, longitudinal study, PROSPECTIVE, long-term study, prospective, Study, Longitudinal, Longitudinal Study, Longitudinal Studies**\n\nMy question then is might that information be useful at the very least as a method for identifying  unlabelled datasets in the training data?"
  }
}