Multi-Task Learning in Natural Language Processing: An Overview
ACM Computing Surveys · 31.12.2024 · 56 (12) · 1-32
DOI: 10.1145/3663363 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 25.07.2024. Verfasst von Shijie Chen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 122-mal zitiert (Crossref) und nennt 171 Literaturangaben. Gefördert von: NSFC, NSFC general, Shenzhen fundamental research program.
Abstract (Originalsprache)
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.
Förderung
- NSFC
- NSFC general
- Shenzhen fundamental research program
Zitieren
APA
Chen, S., Zhang, Y., & Yang, Q. (2024). Multi-Task Learning in Natural Language Processing: An Overview. ACM Computing Surveys, 56(12), 1-32. https://doi.org/10.1145/3663363
Vancouver
Chen S, Zhang Y, Yang Q. Multi-Task Learning in Natural Language Processing: An Overview. ACM Computing Surveys. 2024;56(12):1-32. doi:10.1145/3663363
BibTeX
@article{Chen2024,
author = {Chen, Shijie and Zhang, Yu and Yang, Qiang},
title = {Multi-Task Learning in Natural Language Processing: An Overview},
journal = {ACM Computing Surveys},
year = {2024},
volume = {56},
number = {12},
pages = {1--32},
doi = {10.1145/3663363}
}
EUVIMED