返回
Multi-Task Learning in Natural Language Processing: An Overview
DOI:10.1145/3663363.png)
摘要
En 中文
Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP). However, directly training deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks. In recent years, Multi-Task Learning (MTL), which can leverage useful information of related tasks to achieve simultaneous performance improvement on these tasks, has been used to handle these problems. In this article, we give an overview of the use of MTL in NLP tasks. We first review MTL architectures used in NLP tasks and categorize them into four classes, including parallel architecture, hierarchical architecture, modular architecture, and generative adversarial architecture. Then we present optimization techniques on loss construction, gradient regularization, data sampling, and task scheduling to properly train a multi-task model. After presenting applications of MTL in a variety of NLP tasks, we introduce some benchmark datasets. Finally, we make a conclusion and discuss several possible research directions in this field.
Keyword:
Multi-task learning
期刊
IF:
28
论文数:
2.4K
被引数:
3.5W
机构
引用论文
Tumour‐associated changes in intestinal epithelial cells cause local accumulation of KLRG1+GATA3+ regulatory T cells in mice
Immunology
IF0
Quantitative and qualitative alterations of circulating myeloid cells and plasmacytoid DC in SARS‐CoV‐2 infection
Immunology
IF0
The role of carbon from recycled sediments in the origin of ultrapotassic igneous rocks in the Central Mediterranean
Lithos
IF0
The generation, segregation, ascent and emplacement of granite magma: the migmatite-to-crustally-derived granite connection in thickened orogens花岗岩岩浆的产生,偏析,上升和沉积: 增厚造山带中混合岩到地壳的花岗岩连接

