Embedding Regularization
Embedding Regularization is a computational technique in natural language processing that belongs to the class of regularization methods, specifically designed to constrain the learned representations of words in a continuous vector space to improve generalization by reducing overfitting, enhancing semantic coherence, or enforcing desirable geometric properties.
60
Publications
4.7K
Citations
216
Authors
91
Institutions
Publications per year
2017–2026
49
Parents
60
A Structured Self-attentive Sentence Embedding
Zhouhan Lin, Minwei Feng, Cícero Nogueira dos Santos et al. · arXiv (Cornell University) · 2017 · 1.5K citations · Full text
Weight Poisoning Attacks on Pretrained Models
Keita Kurita, Paul Michel, Graham Neubig · 2020 · 316 citations · Full text
1–5 of 60
216
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 216
91

Peking University
Beijing, China
6 h-index
17 publications
679 citations

Hong Kong University of Science and Technology
Hong Kong, Hong Kong
3 h-index
7 publications
81 citations

Beijing University of Posts and Telecommunications
Beijing, China
3 h-index
7 publications
206 citations
Jiangsu University
Zhenjiang, China
2 h-index
4 publications
134 citations

Tel Aviv University
Tel Aviv, Israel
2 h-index
6 publications
394 citations
Shandong Institute of Automation
Jinan, China
2 h-index
2 publications
67 citations
Google (United States)
Mountain View, United States
2 h-index
7 publications
417 citations
Nanjing University
Nanjing, China
2 h-index
4 publications
141 citations
1–8 of 91
Repository · 13 publications · 2.2K citations
11
h-index
Conference · 5 publications · 368 citations
5
h-index
3 publications · 95 citations
3
h-index
2 publications · 48 citations
2
h-index
Conference · 2 publications · 65 citations
2
h-index
1–5