CRF-based Learning Algorithm: Difference between revisions

From GM-RKB
Jump to navigation Jump to search
m (Remove links to pages that are actually redirects to this page.)
m (Remove links to pages that are actually redirects to this page.)
Line 1: Line 1:
A [[CRF-based Learning Algorithm]] is a [[Maximum Entropy-based Learning Algorithm]] that trains a [[Conditional Random Field Model]].
A [[CRF-based Learning Algorithm]] is a [[Maximum Entropy-based Learning Algorithm]] that trains a [[Conditional Random Field Model]].
* <B>AKA:</B> [[CRF Training Algorithm]], [[CRF-based Learning Algorithm|Conditional Random Field Learning Algorithm]], [[CRF Algorithm]], [[CRF-based Learning Algorithm|Conditional Random Field Modeling Algorithm]].
* <B>AKA:</B> [[CRF Training Algorithm]], [[CRF-based Learning Algorithm|Conditional Random Field Learning Algorithm]], [[CRF-based Learning Algorithm|CRF Algorithm]], [[CRF-based Learning Algorithm|Conditional Random Field Modeling Algorithm]].
* <B>Context</U>:</B>
* <B>Context</U>:</B>
** It can require a [[Parameter Estimation Algorithm]].
** It can require a [[Parameter Estimation Algorithm]].

Revision as of 20:03, 23 December 2019

A CRF-based Learning Algorithm is a Maximum Entropy-based Learning Algorithm that trains a Conditional Random Field Model.



References

2009

  • (Wikipedia, 2009) ⇒ http://en.wikipedia.org/wiki/Conditional_random_field
    • A conditional random field (CRF) is a type of discriminative probabilistic model most often used for the labeling or parsing of sequential data, such as natural language text or biological sequences.

2003

2001

of G. Then (X,Y) is a conditional random field in case, when conditioned on X, the random variables Yv obey the Markov property with respect to the graph: p(Yv |X,Yw,w 6= v) = p(Yv |X,Yw,w v), where [math]\displaystyle{ w }[/math] v means that [math]\displaystyle{ w }[/math] and v are neighbors in G."