An Empirical Study of Smoothing Techniques for Language Modeling.¶
Chen, S. F., & Goodman, J. (1996). An Empirical Study of Smoothing Techniques for Language Modeling. Proceedings of the 34th Annual Meeting of the ACL, 310-318.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Cromwell's Rule
- Machine learning and language modeling — zero-count events destroy probability estimates and yield undefined perplexity; smoothing methods (Laplace, Good–Turing, Kneser–Ney, backoff) exist precisely to keep unseen events at small but nonzero probability.
This sourceSurveys and compares smoothing methods (add-one/Laplace, Good–Turing, Kneser–Ney, backoff) that keep unseen events at small but nonzero probability.
- Machine learning and language modeling — zero-count events destroy probability estimates and yield undefined perplexity; smoothing methods (Laplace, Good–Turing, Kneser–Ney, backoff) exist precisely to keep unseen events at small but nonzero probability.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:74077e16c61d · see in the full table