|
Reranker Framework (ReFr)
Reranking framework for structure prediction and discriminative language modeling
|
All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Pages
|
Reranker Framework (ReFr)
Reranking framework for structure prediction and discriminative language modeling
|
This candidate set scorer picks two candidates at random from the set, scores them and then identifies which has the higher score and the lowest loss, effectively meaning that training proceeds as if those were the only two candidates. More...
#include <model.H>
Public Member Functions | |
| virtual void | Init (const Environment *env, const string &arg) |
Initializes the random seed using srand and the current time available by calling time(NULL). More... | |
| virtual void | Score (Model *model, CandidateSet &candidates, bool training) |
| Picks two candidates at random from the set, scores them and then identifies which has the higher score and the lowest loss, effectively meaning that training proceeds as if those were the only two candidates. More... | |
 Public Member Functions inherited from reranker::FactoryConstructible | |
| virtual | ~FactoryConstructible () |
| virtual void | RegisterInitializers (Initializers &initializers) |
This candidate set scorer picks two candidates at random from the set, scores them and then identifies which has the higher score and the lowest loss, effectively meaning that training proceeds as if those were the only two candidates.
|
virtual |
Initializes the random seed using srand and the current time available by calling time(NULL).
Reimplemented from reranker::FactoryConstructible.
|
virtual |
Picks two candidates at random from the set, scores them and then identifies which has the higher score and the lowest loss, effectively meaning that training proceeds as if those were the only two candidates.
Implements reranker::CandidateSet::Scorer.
1.8.6