Package nltk :: Package model :: Module ngram :: Class NgramModel

type NgramModel

object --+    
         |    
api.ModelI --+
             |
            NgramModel

A processing interface for assigning a probability to the next word.

Instance Methods

[hide private]

__init__(self, n, train, estimator=None)
Creates an ngram language model to capture patterns in n consecutive words of training text.

source code

prob(self, word, context)
Evaluate the probability of this word in this context.

source code

_alpha(self, tokens)

source code

_beta(self, tokens)

source code

logprob(self, word, context)
Evaluate the (negative) log probability of this word in this context.

source code

choose_random_word(self, context)
Randomly select a word that is likely to appear in this context.

source code

generate(self, num_words, context=())
Generate random text based on the language model. source code

_generate_one(self, context)

source code

entropy(self, text)
Evaluate the total entropy of a text with respect to the model.

source code

__contains__(self, item)

source code

__getitem__(self, item)

source code

__repr__(self)

source code

Method Details

[hide private]

init(self, n, train, estimator=None)
(Constructor)

source code

Creates an ngram language model to capture patterns in n consecutive words of training text. An estimator smooths the probabilities derived from the text and may allow generation of ngrams not seen during training.

Parameters:

n (int) - the order of the language model (ngram size)
train (list of string) - the training text
estimator (a function that takes a ConditionalFreqDist and returns a ConditionalProbDist) - a function for generating a probability distribution

Overrides: api.ModelI.__init__