Multi Task Learning in Natural Language Processing - Barbara Plank

preview_player
Показать описание
A talk given at the conference WASP4ALL 2020 - Virtual Worlds for Artificial Intelligence.

Barbara Plank is Associate Professor at IT University of Copenhagen.

Abstract
Despite recent success in Natural Language Processing (NLP), our models still dreadfully lack the ability to generalize to conditions that are different from the ones encountered during training or problems for which training data is scarce. Such adverse conditions include learning for noisy domains up to the extreme case of adaptation: new languages. Multi-Task Learning (MTL) is a method that can help remedy this problem. In this talk I will discuss MTL and applications within NLP.
  1. WASP Research Program
Рекомендации по теме
Multi-Task Learning | 0:05:40

Multi-Task Learning | Explained in 5 Minutes

Multi Task Learning 0:31:49

Multi Task Learning in Natural Language Processing - Barbara Plank

MultiTask Learning with 0:21:35

MultiTask Learning with NLP

Neural networks [10.10] 0:16:03

Neural networks [10.10] : Natural language processing - multitask learning

Multi-task learning - 0:13:00

Multi-task learning - Structuring Machine Learning Projects

CS 152 NN—16: 0:06:46

CS 152 NN—16: Multi task Learning

Leveraging neural network 0:40:18

Leveraging neural network multi-task learning for passenger forecasts

Learning to execute 0:01:31

Learning to execute natural language instructions (Multitask Learning)

LLMs | LLMs 0:55:15

LLMs | LLMs and Tools: Function Calling | Lec 18.2

Shen Liang - 0:46:33

Shen Liang - Deep Transfer Learning and Multi-task Learning + Hands-On Workshop

Personalized Multi-task Learning 0:01:53

Personalized Multi-task Learning for Predicting Tomorrow's Mood, Stress, and Health

Multitask Prompted Training 0:05:44

Multitask Prompted Training Enables Zero-Shot Task Generalization

Calibrated Multi-Task Learning 0:02:25

Calibrated Multi-Task Learning

Natural language processing 0:03:36

Natural language processing - semantic textual similarity - multi task learning

[ICML 2018] Multi-task 0:14:14

[ICML 2018] Multi-task learning

Andrej Karpathy: Tesla 0:23:57

Andrej Karpathy: Tesla Autopilot and Multi-Task Learning for Perception and Prediction

Richard Socher - 0:57:42

Richard Socher - The Natural Language Decathlon: Multitask Learning as Question Answering

Multi-Task Learning for 0:15:09

Multi-Task Learning for QSAR Learning

MulT: An End-to-End 0:04:58

MulT: An End-to-End Multitask Learning Transformer (CVPR 2022)

Hristo Vrigazov: Multi-task 0:34:54

Hristo Vrigazov: Multi-task learning in the real world with Catalyst

Variable Selection and 0:02:15

Variable Selection and Task Grouping for Multi-Task Learning

2018 Multi-Task Learning 0:01:37

2018 Multi-Task Learning

ECCV 2020: Environment-agnostic 0:09:45

ECCV 2020: Environment-agnostic Multitask Learning for Natural Language Grounded Navigation

'Computer Vision and 0:29:49

'Computer Vision and NLP for Multi-Task Fashion Modeling' by Michael Sugimura