Homework 4: Applications of Word Embeddings
Due Thursday March 14, 11:59PM ESTGradescope Colab Notebook Late Day Request Form (accepted up to 24 hours before deadline)
In this homework assignment, we will be exploring exploring word embeddings through the implementation of algorithms from two recent papers.
Learning Goals:
Once you complete this assignment, you should:
- Be familiar with some applications of word embeddings
- Be able to express one way in which word embeddings can replicate human biases
- Have experience reading documentation for a new library to write efficient code
- Have experience turning algorithms from NLP papers into code
- Be familiar with NLP methods in three key areas: text classification, text generation, and language understanding
- Be able to effectively use python libraries that are part of the large ecosystem of tools for NLP
- Be exposed to ways in which language technology can perpetuate stereotypes and biases related to minoritized groups, and inequity among different languages
- Demonstrate your ability to engage with recent research papers in NLP
HW4.ipynb Leaderboard: In the leaderboard for this assignment, you will be ranked according to the number of relevant terms in your top 50 list. See details under task 2.4. Your first two submissions without errors each day will count towards the leaderboard.
Credits: This assignment is inspired by papers written by Aylin Caliskan and Hila Gonen.
When you submit to gradescope, your file must be called exactly HW4.ipynb.
This homework assignment differs from homework assignments 1-3 in that you will complete it in a Colab notebook. The instructions are all listed in the notebook!
To submit this homework, you should download your notebook as a .ipynb file and submit that to gradescope (click File » Download » Download .ipynb). That is the only file you’ll need to submit (it will include your report).