timoschick/pet

 By GitHub - 2020-10-01

Description

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference" - timoschick/pet

Summary

  • 📑 Contents 🔧 Setup All requirements for PET can be found in requirements.txt.
  • $DATA_DIR is the directory containing the train and test files (check tasks.py to see how these files should be named and formatted for each task).
  • You can also define multiple verbalizations for a single label.
  • If you want to use verbalizers that correspond to multiple tokens (as described here), you need to define a custom TaskHelper and add it to the TASK_HELPERS dictionary in pet/tasks.py.

 

Topics

  1. NLP (0.3)
  2. Machine_Learning (0.06)
  3. Backend (0.06)

Similar Articles

K-fold Cross Validation with PyTorch

By MachineCurve - 2021-02-02

Explanations and code examples showing you how to use K-fold Cross Validation for Machine Learning model evaluation/testing with PyTorch.

Creating the Whole Machine Learning Pipeline with PyCaret

By Medium - 2020-12-03

This tutorial covers the entire ML process, from data ingestion, pre-processing, model training, hyper-parameter fitting, predicting and storing the model for later use. We will complete all these…