Active Few-Shot Learning with FASL

04/20/2022
by   Thomas Müller, et al.
6

Recent advances in natural language processing (NLP) have led to strong text classification models for many tasks. However, still often thousands of examples are needed to train models with good quality. This makes it challenging to quickly develop and deploy new models for real world problems and business needs. Few-shot learning and active learning are two lines of research, aimed at tackling this problem. In this work, we combine both lines into FASL, a platform that allows training text classification models using an iterative and fast process. We investigate which active learning methods work best in our few-shot setup. Additionally, we develop a model to predict when to stop annotating. This is relevant as in a few-shot setup we do not have access to a large validation set.

READ FULL TEXT
research
11/15/2022

MEAL: Stable and Active Learning for Few-Shot Prompting

Few-shot classification in NLP has recently made great strides due to th...
research
01/31/2021

A Simple yet Brisk and Efficient Active Learning Platform for Text Classification

In this work, we propose the use of a fully managed machine learning ser...
research
08/17/2020

A Survey of Active Learning for Text Classification using Deep Neural Networks

Natural language processing (NLP) and neural networks (NNs) have both un...
research
08/30/2023

Towards One-Shot Learning for Text Classification using Inductive Logic Programming

With the ever-increasing potential of AI to perform personalised tasks, ...
research
01/27/2022

Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation

Large pretrained language models (LMs) like BERT have improved performan...
research
12/03/2019

A Deep Convolutional Network for Seismic Shot-Gather Image Quality Classification

Deep Learning-based models such as Convolutional Neural Networks, have l...
research
11/24/2022

PyTAIL: Interactive and Incremental Learning of NLP Models with Human in the Loop for Online Data

Online data streams make training machine learning models hard because o...

Please sign up or login with your details

Forgot password? Click here to reset