Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published December 4, 2020 | Version v1
Software Open

Building Location Embeddings from Physical Trajectories and Textual Representations

  • 1. University of Michigan
  • 2. University of Michiagn

Description

Code for building and evaluating location embeddings for the 2020 AACL-IJCNLP paper "Building Location Embeddings from Physical Trajectories and Textual Representations."

Abstract: 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's area of study to a student's depression level, showing the effectiveness of these location embeddings.

Contact: Please contact Laura Biester (lbiester@umich.edu) with questions.

Files

Location-Embeddings.zip

Files (196.7 kB)

Name Size Download all
md5:1f2671cb1cc2fdf33b4429e4eceea890
196.7 kB Preview Download

Additional details

Related works

Is supplement to
Conference paper: https://www.aclweb.org/anthology/2020.aacl-main.44/ (URL)