Maximum-Entropy Markov Model Training Algorithm: Difference between revisions
Jump to navigation
Jump to search
m (Text replacement - "---- __NOTOC__" to "---- __NOTOC__") |
m (Text replacement - "]]↵----" to "]]. ----") |
||
| Line 1: | Line 1: | ||
A [[Maximum-Entropy Markov Model Training Algorithm]] is a [[model training algorithm]] that can be applied by a [[MEMM trainer]] to solve a [[MEMM training task]]. | A [[Maximum-Entropy Markov Model Training Algorithm]] is a [[model training algorithm]] that can be applied by a [[MEMM trainer]] to solve a [[MEMM training task]]. | ||
* <B>See:</B> [[CRF Training Algorithm]] | * <B>See:</B> [[CRF Training Algorithm]]. | ||
---- | ---- | ||
---- | ---- | ||
Latest revision as of 05:19, 28 November 2023
A Maximum-Entropy Markov Model Training Algorithm is a model training algorithm that can be applied by a MEMM trainer to solve a MEMM training task.
- See: CRF Training Algorithm.
References
2016
- http://www.datasciencecentral.com/profiles/blogs/conditional-random-fields-crf-short-survey
- QUOTE: The most similar method for CRF is MEMM (Maximum-entropy Markov Model). It is also discriminative probabilistic graphical model. However, MEMM has so called “label bias problem” (see, for example, this link for details or this link). CRF has no such problem and this fact is the main difference between CRF and MEMM.