Clustering Examples in Multi-Task NLP Benchmarks with Item Response Theory

Welcome to the project page for our workshop paper appearing at the Workshop on Insights from Negative Results in NLP (co-located with ACL 2022).

Abstract

Coming soon

Citation

Coming soon

Code

We have open sourced our model and paper code at the links below. Instructions to reproduce our results are in each respective repository.

• Model code: github.com/entilzha/multidim-irt
• Paper latex: github.com/entilzha/publications

Data

Coming soon

Contact

Please contact Pedro Rodriguez at me@pedro.ai