Multi-Task Learning
449 papers with code • 7 benchmarks • 41 datasets
Multi-task learning aims to learn multiple different tasks simultaneously while maximizing performance on one or all of the tasks.
( Image credit: Cross-stitch Networks for Multi-task Learning )
Benchmarks
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
CIFAR-100
Cityscapes
CelebA
Omniglot
CELEX
Aff-Wild2
KP20k
THCHS-30
WIDER
Greatest papers with code
Semi-Supervised Sequence Modeling with Cross-View Training
tensorflow/models
•
•
EMNLP 2018
We therefore propose Cross-View Training (CVT), a semi-supervised learning algorithm that improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data.
Ranked #1 on
CCG Supertagging
on CCGbank
DRAGNN: A Transition-based Framework for Dynamically Connected Neural Networks
In this work, we present a compact, modular framework for constructing novel recurrent neural architectures.
fairseq S2T: Fast Speech-to-Text Modeling with fairseq
huggingface/transformers
•
•
Asian Chapter of the Association for Computational Linguistics 2020
We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation.
Ranked #4 on
Speech-to-Text Translation
on MuST-C EN->DE
Language Models are Unsupervised Multitask Learners
huggingface/transformers
•
•
Preprint 2019
Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
Ranked #1 on
Language Modelling
on enwik8
(using extra training data)
Pentagon at MEDIQA 2019: Multi-task Learning for Filtering and Re-ranking Answers using Language Inference and Question Entailment
google-research/bert
•
•
WS 2019
Parallel deep learning architectures like fine-tuned BERT and MT-DNN, have quickly become the state of the art, bypassing previous deep and shallow learning methods by a large margin.
DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning
google-research/google-research
•
•
State-of-the-art MoE models use a trainable sparse gate to select a subset of the experts for each input example.
A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
Detecting scene text of arbitrary shapes has been a challenging task over the past years.
One Model To Learn Them All
We present a single model that yields good results on a number of problems spanning multiple domains.
A Unified Framework for Structured Low-rank Matrix Learning
microsoft/recommenders
•
•
ICML 2018
We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices.
Language Models are Few-Shot Learners
By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.
Ranked #1 on
Question Answering
on PIQA