To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP

To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP

Data-hungry deep neural networks have established themselves as the de facto standard for many NLP tasks, including the traditional sequence tagging ones. Despite their state-of-the-art performance on high-resource languages, they still fall behind their statistical counterparts in low-resource scen...

Full description

Bibliographic Details
Main Author: Şahin, G.G (Author)
Format: Article
Language:English
Published: MIT Press Journals 2022
Subjects:
Augmentation techniques
Character level
Comparatives studies
Computational linguistics
De facto standard
Deep neural networks
Dependency parsing
Natural language processing systems
Part of speech tagging
Parts-of-speech tagging
Semantic role labeling
Semantics
State-of-the-art performance
Syntactics
Synthetic training data
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items