Language Model Smoothing is a statistical technique used in probabilistic information retrieval that adjusts the probability estimates of a language model to account for unseen or rare word sequences by redistributing probability mass from observed events to unobserved ones, thereby preventing zero probabilities and improving generalization.
108
Publications
15.5K
Citations
237
Authors
89
Institutions
Publications per year
2017–2026
8
Parents
Publications
108
1–5 of 108
Authors
237
- CZ
7
h-index
- HN
5
h-index
- JL
4
h-index
- SF
4
h-index
- RK
4
h-index
1–5 of 237
Institutions
89
Carnegie Mellon University
Pittsburgh, United States
10 h-index
18 publications
10.5K citations
Microsoft (United States)
Redmond, United States
5 h-index
8 publications
2.3K citations
Microsoft Research (United Kingdom)
Cambridge, United Kingdom
4 h-index
5 publications
2.6K citations
University of Illinois Urbana-Champaign
Urbana, United States
4 h-index
8 publications
379 citations
University of Edinburgh
Edinburgh, United Kingdom
4 h-index
7 publications
382 citations
University of Massachusetts Amherst
Amherst Center, United States
4 h-index
8 publications
913 citations
Google (United States)
Mountain View, United States
3 h-index
13 publications
369 citations
Tilburg University
Tilburg, The Netherlands
3 h-index
6 publications
170 citations
1–8 of 89
Venues
- arXiv (Cornell University)
Repository · 3 publications · 275 citations
3
h-index
- ArXiv.org
Repository · 2 publications · 772 citations
2
h-index
- IEEE Transactions on Audio Speech and Language Processing
2 publications · 115 citations
2
h-index
- Information Retrieval
2 publications · 67 citations
2
h-index
- International Journal of Computational Intelligence Systems
IJCIS · 2 publications · 26 citations
2
h-index
1–5