featuregenerator.lm.srilm.srilm_ngram.SRILMngramGenerator

Class SRILMngramGenerator

object --+ | featuregenerator.FeatureGenerator --+ | languagefeaturegenerator.LanguageFeatureGenerator --+ | SRILMngramGenerator

Gets all the words of a sentence through a SRILM language model and counts how many of them are unknown (unigram prob -99)

Instance Methods

[hide private]

__init__(self, url, lang='en', lowercase=True, tokenize=True, freqcase_file=False)
Define connection with the server source code

get_features_src(self, simplesentence, parallelsentence)
Function that falls back to the general simple sentence feature generation, only if the language is supported by the feature generator It receives a source simple sentence and returns a list of source features.

source code

get_features_tgt(self, simplesentence, parallelsentence)
Function that falls back to the general simple sentence feature generation, only if the language is supported by the feature generator It receives a target simple sentence and returns a list of target features.

source code

_prepare_sentence(self, simplesentence)

source code

prepare_sentence(self, simplesentence)

source code

_standouts(self, vector, sign)

source code

_standout_pos(self, vector, sign)

source code

get_features_simplesentence(self, simplesentence)
Abstract method to be overriden by the particular subclassed feature generator.

source code

_get_sentence_probability(self, sent_string)

source code

xmlrpc_call(self, batch)

source code

Inherited from languagefeaturegenerator.LanguageFeatureGenerator: add_features_batch, add_features_batch_xml, add_features_dataset, get_features_string

Inherited from featuregenerator.FeatureGenerator: add_features_parallelsentence, add_features_simplesentence, add_features_src, add_features_tgt, get_annotation_name, get_features_parallelsentence, process_dataset

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __repr__, __setattr__, __sizeof__, __str__, __subclasshook__

Properties

[hide private]

Inherited from object: __class__

init(self, url, lang=`'en'`, lowercase=True, tokenize=True, freqcase_file=False)
(Constructor)

source code

Define connection with the server

Parameters:

lang - the language code of the language that the feature generator is capable of

Overrides: object.__init__

get_features_src(self, simplesentence, parallelsentence)

source code

Function that falls back to the general simple sentence feature generation, only if the language is supported by the feature generator It receives a source simple sentence and returns a list of source features.

Overrides: featuregenerator.FeatureGenerator.get_features_src: (inherited documentation)

get_features_tgt(self, simplesentence, parallelsentence)

source code

Function that falls back to the general simple sentence feature generation, only if the language is supported by the feature generator It receives a target simple sentence and returns a list of target features.

Overrides: featuregenerator.FeatureGenerator.get_features_tgt: (inherited documentation)

get_features_simplesentence(self, simplesentence)

source code

Abstract method to be overriden by the particular subclassed feature generator. It receives a simple sentence of any type and returns a list of features. It should be overriden by a feature generator that doesn't differentiate between source and target features

Overrides: featuregenerator.FeatureGenerator.get_features_simplesentence: (inherited documentation)

Class SRILMngramGenerator

__init__(self, url, lang='en', lowercase=True, tokenize=True, freqcase_file=False) (Constructor)

get_features_src(self, simplesentence, parallelsentence)

get_features_tgt(self, simplesentence, parallelsentence)

get_features_simplesentence(self, simplesentence)

init(self, url, lang=`'en'`, lowercase=True, tokenize=True, freqcase_file=False)
(Constructor)