https://github.com/sandeepsoni/comparing-word2vec-models
Code, data, and notes for tutorial on using word embeddings to find variation and change
https://github.com/sandeepsoni/comparing-word2vec-models
tutorial
Last synced: 6 months ago
JSON representation
Code, data, and notes for tutorial on using word embeddings to find variation and change
- Host: GitHub
- URL: https://github.com/sandeepsoni/comparing-word2vec-models
- Owner: sandeepsoni
- License: apache-2.0
- Created: 2021-09-24T18:29:52.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2022-06-06T06:00:04.000Z (over 3 years ago)
- Last Synced: 2025-02-25T03:23:34.727Z (11 months ago)
- Topics: tutorial
- Homepage:
- Size: 36.5 MB
- Stars: 1
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Tutorial on Word Embeddings
This tutorial introduces word embeddings. The tutorial is catered for social science and digital humanities practitioners who are new to NLP. The objective of the tutorial is to explain briefly the concept of word embeddings and contextual embeddings, introduce method with code to learn embeddings, and demonstrate a specific application of embeddings in finding variation and change.
There are two versions of the tutorial. The first version was created by [Conor Golroy](https://ccgilroy.com/) and [Sandeep Soni](https://sandeepsoni.github.io/). It was presented virtually in the [NLP+CSS 201 Tutorials series](https://nlp-css-201-tutorials.github.io/nlp-css-201-tutorials/). You can checkout the [notebook](https://colab.research.google.com/drive/16cM5NXedlrvU2mp-HcYKs9OIMkYItTS1?usp=sharing) and the [video](https://youtu.be/WbzPZZKJRJA) of the tutorial.
The second version of the tutorial was developed by [Sandeep Soni](https://sandeepsoni.github.io/) and is to be presented at [ICWSM, 2022](https://www.icwsm.org/2022/index.html/) virtually. This tutorial follows the earlier tutorial except it also demonstrates the use of contextual embeddings to measure variation and change. You can checkout the [notebook](https://colab.research.google.com/drive/1fhrdt8G1H8LFO1KFooQ3jMF9jfE8TT_K?usp=sharing) here.