Interface for exploring semantic spaces. The interface can be run either locally or as a web server.
If you wish to modify this code, it's helpful to have a decent understanding of Python, HTML, CSS. A basic understanding of APIs and making websites is also handy. Familiarity with the Python libraries Pandas, Flask, and scikit-learn can be helpful.
Please see the wiki for this repository
Download the project from this git repository, install all Python requirements in requirements.txt. Paths may have to be changed in the configuration file "/home/vectorswebtool/vectors-webtool/config.ini," especially to add the path for the vector space on your local machine, which you should put into the /data/ folder.
Then, simply run the python file "/home/vectorswebtool/vectors-webtool/snaut-english/snaut.py" in your favorite Python IDE and go to http://localhost:15100/ if it doesn't open automatically.
It may reload several times over the course of a few minutes before you see the site, especially if the vector space is large. Don't worry, this is normal behavior.
This tool is based on the snaut tool, which was developed at Center for Reading Research, Ghent University by Paweł Mandera.
The project is licensed under the Apache License 2.0.
Günther, F., Marelli, M., Tureski, S, & Petilli, M. (2021). ViSpa (Vision Spaces): A computer-vision-based representation system for individual images and concept prototypes, with large-scale evaluation. psyArXiV preprint. https://doi.org/10.31234/osf.io/n4dmq
Mandera, P., Keuleers, E., & Brysbaert, M. (in press). Explaining human performance in psycholinguistic tasks with models of semantic similarity based on prediction and counting: A review and empirical validation. Journal of Memory and Language.