.png){kind=icon}
Return
Low-resource text classification using domain-adversarial learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.csl.2019.101056.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep learning techniques have recently shown to be successful in many natural language processing tasks forming state-of-the-art systems. They require, however, a large amount of annotated data which is often missing. This paper explores the use of domain-adversarial learning as a regularizer to avoid overfitting when training domain invariant features for deep, complex neural networks in low-resource and zero-resource settings in new target domains or languages. In case of new languages, we show that monolingual word vectors can be directly used for training without prealignment. Their projection into a common space can be learnt ad-hoc at training time reaching the final performance of pretrained multilingual word vectors. (C) 2019 Elsevier Ltd. All rights reserved.
Keywords:
NLP
Low-resource
Deep learning
Domain-adversarial
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
C
IF:
3.4
Papers:
1.5K
Citations:
2.6K
Organization
Cited Papers
Can CD34 discriminate between benign and malignant hepatocytic lesions in fine-needle aspirates and thin core biopsies?.png)
CancerOAAI
CancerIF0
OAAIShareSave
ShareSaveEnhancement of pyramid solar distiller performance using reflectors, cooling cycle, and dangled cords of wicksDesalination
DesalinationIF0
PREAI
ShareSaveEffect of lovastatin on behavior in children and adults with fragile X syndrome: An open‐label study
PREAI
ShareSaveShareSaveShareSave
View more