Software Open Access

Building Location Embeddings from Physical Trajectories and Textual Representations

Biester, Laura; Banea, Carmen; Mihalcea, Rada


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/b785783d-7b96-4865-b4ac-81368377365d/Location-Embeddings.zip"
      }, 
      "checksum": "md5:1f2671cb1cc2fdf33b4429e4eceea890", 
      "bucket": "b785783d-7b96-4865-b4ac-81368377365d", 
      "key": "Location-Embeddings.zip", 
      "type": "zip", 
      "size": 196657
    }
  ], 
  "owners": [
    191523
  ], 
  "doi": "10.5281/zenodo.4479440", 
  "stats": {
    "version_unique_downloads": 3.0, 
    "unique_views": 28.0, 
    "views": 34.0, 
    "version_views": 34.0, 
    "unique_downloads": 3.0, 
    "version_unique_views": 28.0, 
    "volume": 589971.0, 
    "version_downloads": 3.0, 
    "downloads": 3.0, 
    "version_volume": 589971.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.4479440", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.4479439", 
    "bucket": "https://zenodo.org/api/files/b785783d-7b96-4865-b4ac-81368377365d", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.4479439.svg", 
    "html": "https://zenodo.org/record/4479440", 
    "latest_html": "https://zenodo.org/record/4479440", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.4479440.svg", 
    "latest": "https://zenodo.org/api/records/4479440"
  }, 
  "conceptdoi": "10.5281/zenodo.4479439", 
  "created": "2021-01-29T19:51:05.886629+00:00", 
  "updated": "2021-01-30T00:27:09.560651+00:00", 
  "conceptrecid": "4479439", 
  "revision": 2, 
  "id": 4479440, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.4479440", 
    "description": "<p>Code for building and evaluating location embeddings for the 2020 AACL-IJCNLP&nbsp;paper &quot;Building Location Embeddings from Physical Trajectories and Textual Representations.&quot;</p>\n\n<p><strong>Abstract:&nbsp;</strong>Word embedding methods have become the de-facto way to represent words, having been successfully applied to a wide array of natural language processing tasks. In this paper, we explore the hypothesis that embedding methods can also be effectively used to represent spatial locations. Using a new dataset consisting of the location trajectories of 729 students over a seven month period and text data related to those locations, we implement several strategies to create location embeddings, which we then use to create embeddings of the sequences of locations a student has visited. To identify the surface level properties captured in the representations, we propose a number of probing tasks such as the presence of a specific location in a sequence or the type of activities that take place at a location. We then leverage the representations we generated and employ them in more complex downstream tasks ranging from predicting a student&#39;s area of study to a student&#39;s depression level, showing the effectiveness of these location embeddings.</p>\n\n<p><strong>Contact:</strong>&nbsp;Please contact Laura Biester (lbiester@umich.edu) with questions.</p>", 
    "language": "eng", 
    "title": "Building Location Embeddings from Physical Trajectories and Textual Representations", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "4479439"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "4479440"
          }
        }
      ]
    }, 
    "publication_date": "2020-12-04", 
    "creators": [
      {
        "orcid": "0000-0003-3901-2968", 
        "affiliation": "University of Michigan", 
        "name": "Biester, Laura"
      }, 
      {
        "affiliation": "University of Michigan", 
        "name": "Banea, Carmen"
      }, 
      {
        "affiliation": "University of Michiagn", 
        "name": "Mihalcea, Rada"
      }
    ], 
    "meeting": {
      "acronym": "AACL-IJCNLP 2020", 
      "url": "http://aacl2020.org/", 
      "dates": "4-7 December, 2020", 
      "place": "Virtual", 
      "title": "1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing"
    }, 
    "access_right": "open", 
    "resource_type": {
      "type": "software", 
      "title": "Software"
    }, 
    "related_identifiers": [
      {
        "scheme": "url", 
        "identifier": "https://www.aclweb.org/anthology/2020.aacl-main.44/", 
        "relation": "isSupplementTo", 
        "resource_type": "publication-conferencepaper"
      }, 
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.4479439", 
        "relation": "isVersionOf"
      }
    ]
  }
}
34
3
views
downloads
All versions This version
Views 3434
Downloads 33
Data volume 590.0 kB590.0 kB
Unique views 2828
Unique downloads 33

Share

Cite as