Reranker Framework (ReFr)
Reranking framework for structure prediction and discriminative language modeling
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Pages
Classes | Namespaces | Macros
perceptron-model.H File Reference

Provides the reranker::PerceptronModel reranker class. More...

#include <vector>
#include <unordered_set>
#include <memory>
#include "candidate-set.H"
#include "dot-product.H"
#include "model.H"
#include "training-time.H"
#include "training-vector-set.H"

Go to the source code of this file.

Classes

class  reranker::PerceptronModel
 This class implements a perceptron model reranker. More...
 
class  reranker::PerceptronModel::DefaultUpdatePredicate
 The default update predicate for perceptron and perceptron-style models, which indicates to do a model update whenever the top-scoring candidate hypothesis under the current model differs from the oracle or “gold” candidate hypothesis. More...
 
class  reranker::PerceptronModel::DefaultUpdater
 The default update function for perceptron models. More...
 

Namespaces

 reranker
 Provides reranking models for discriminative modeling, with some special handling for discriminative language models.
 

Macros

#define DEFAULT_MAX_EPOCHS_IN_DECLINE   5
 

Detailed Description

Provides the reranker::PerceptronModel reranker class.

Author
dbike.nosp@m.l@go.nosp@m.ogle..nosp@m.com (Dan Bikel)

Definition in file perceptron-model.H.

Macro Definition Documentation

#define DEFAULT_MAX_EPOCHS_IN_DECLINE   5

Definition at line 49 of file perceptron-model.H.