10.5281/zenodo.4479440
https://zenodo.org/records/4479440
oai:zenodo.org:4479440
Biester, Laura
Laura
Biester
0000-0003-3901-2968
University of Michigan
Banea, Carmen
Carmen
Banea
University of Michigan
Mihalcea, Rada
Rada
Mihalcea
University of Michiagn
Building Location Embeddings from Physical Trajectories and Textual Representations
Zenodo
2020
2020-12-04
eng
https://www.aclweb.org/anthology/2020.aacl-main.44/
10.5281/zenodo.4479439
Creative Commons Attribution 4.0 International
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.