Generative Response Generation is a computational approach in dialogue systems that belongs to the class of response generation methods, distinguished by its use of generative models to produce fluent, contextually appropriate responses de novo rather than selecting from or retrieving pre-existing utterances.
221
Publications
16.6K
Citations
749
Authors
214
Institutions
Publications per year
2017–2026
194
Parents
Publications
221
DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation
Yizhe Zhang, Siqi Sun, Michel Galley et al. · 2020 · 1.1K citations · Full text
1–5 of 221
Authors
749
- CB
13
h-index
- BD
13
h-index
- MG
12
h-index
- JG
12
h-index
- RY
8
h-index
1–5 of 749
Institutions
214
Microsoft (United States)
Redmond, United States
12 h-index
56 publications
10.3K citations
Peking University
Beijing, China
11 h-index
38 publications
2.7K citations
Tencent (China)
Shenzhen, China
11 h-index
26 publications
1.4K citations
Tsinghua University
Beijing, China
10 h-index
21 publications
1.8K citations
Harbin Institute of Technology
Harbin, China
10 h-index
33 publications
1.5K citations
Chinese Academy of Sciences
Beijing, China
9 h-index
32 publications
1.4K citations
Beihang University
Beijing, China
8 h-index
25 publications
948 citations
Microsoft Research Asia (China)
Beijing, China
8 h-index
31 publications
1.6K citations
1–8 of 214
Venues
- arXiv (Cornell University)
Repository · 56 publications · 2.4K citations
25
h-index
- Proceedings of the AAAI Conference on Artificial Intelligence
Conference · 15 publications · 1.1K citations
13
h-index
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Conference · 4 publications · 147 citations
4
h-index
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Conference · 4 publications · 262 citations
4
h-index
- IEEE Access
4 publications · 92 citations
3
h-index
1–5