Contextual Embeddings is a representational method in natural language processing that generates vector representations of words or tokens dynamically based on their surrounding linguistic context, thereby capturing polysemy and syntactic nuances unlike static embedding approaches.
618
Publications
47K
Citations
1.9K
Authors
579
Institutions
Publications per year
2017–2026
543
Parents
Publications
618
BERTScore: Evaluating Text Generation with BERT
Tianyi Zhang, Varsha Kishore, Felix Wu et al. · arXiv (Cornell University) · 2019 · 2K citations · Full text
Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification
Duyu Tang, Furu Wei, Nan Yang et al. · 2014 · 1.2K citations · Full text
1–5 of 618
Authors
1.9K
- NA
7
h-index
- FW
6
h-index
- YZ
6
h-index
- HS
6
h-index
- MT
6
h-index
1–5 of 1.9K
Institutions
579
Google (United States)
Mountain View, United States
17 h-index
71 publications
9.8K citations
Carnegie Mellon University
Pittsburgh, United States
14 h-index
45 publications
6.2K citations
Stanford University
Stanford, United States
14 h-index
32 publications
7.2K citations
University of Washington
Seattle, United States
11 h-index
24 publications
2.5K citations
Tsinghua University
Beijing, China
11 h-index
42 publications
2.6K citations
Nanyang Technological University
Singapore, Singapore
10 h-index
14 publications
1.7K citations
Chinese Academy of Sciences
Beijing, China
10 h-index
31 publications
2.6K citations
Harbin Institute of Technology
Harbin, China
9 h-index
20 publications
5.1K citations
1–8 of 579
Venues
- arXiv (Cornell University)
Repository · 90 publications · 7.8K citations
36
h-index
- IEEE Access
16 publications · 1.3K citations
16
h-index
- Proceedings of the AAAI Conference on Artificial Intelligence
Conference · 21 publications · 1.7K citations
14
h-index
- Knowledge-Based Systems
9 publications · 283 citations
9
h-index
- Procedia Computer Science
6 publications · 150 citations
6
h-index
1–5