Multi-task Learning


A subfield of machine learning in which multiple learning tasks are solved at the same time, while exploiting commonalities and differences across tasks.

Overview

An Overview of Multi-Task Learning in Deep Neural Networks
This post gives a general overview of the current state of multi-task learning.
multi-task-learning tutorial article

Tutorials

CS330: Deep Multi-Task and Meta Learning
Study how the structure arising from multiple tasks can be leveraged to learn more efficiently or effectively.
multi-task-learning meta-learning cs330 stanford
MT-Clinical BERT
Scaling Clinical Information Extraction with Multitask Learning
health multi-task-learning information-extraction clinical-information-extraction
Transfer Learning with T5: the Text-To-Text Transfer Transformer
In the paper, we demonstrate how to achieve state-of-the-art results on multiple NLP tasks using a text-to-text transformer pre-trained on a large text ...
transformers t5 question-answering reading-comprehension
ViLBERT-MT: Multi-Task Vision & Language Representation Learning
A single ViLBERT Multi-Task model can perform 8 different vision and language tasks learnt from 12 datasets!
visual-question-answering image-captioning multi-modal computer-vision

Libraries

General
Multi-task-NLP
A utility toolkit enabling NLP developers to easily train and infer a single model for multiple tasks.
multi-task-learning natural-language-processing transformers bert
Table of Contents
Share a project
Share something you or the community has made with ML.
Topic experts
Share