Welcome to the Few Shot Learning NLP Library Documentation

This library provides tools and utilities for Few Shot Learning in Natural Language Processing (NLP).

Installation

You can install this library via pip:

pip install -U few-shot-learning-nlp

Overview

Few Shot Learning in NLP involves training and evaluating models on tasks with limited labeled data. This library offers functionalities to facilitate this process.

Supported Approachs

Text Classification

• Sentence Transformers Finetuning (SetFit)
• Pattern Exploiting Training (PET)

Named Entity Recognition for Image Documents

• Pattern Exploiting Training (PET)
• CLASSBITE
• ContaiNER

Classification utils

• Focal Loss function for imbalanced datasets
• Stratified train test split

Usage

To utilize this library, import the necessary classes and methods and follow the provided documentation for each component.