Returns a list of algorithms that are registered in the engine
Appends new alignment memory to the engine. Adding alignment memory improves the quality of predictions.
a list of alignments
Appends new corpus to the engine.
an array of tokenized source sentences.
an array of tokenized target sentences.
Removes all of the alignment memory from the engine.
Executes prediction algorithms on the unaligned sentence pair. The sentence tokens should contain positional metrics for better accuracy.
the source sentence tokens.
the target sentence tokens.
Adds a new algorithm to the engine.
the algorithm to run with the engine.
Performs the prediction calculations
Generates the final confidence scores and sorts the predictions.
Scores the predictions and returns a filtered set of suggestions TODO: this should not be done in the engine because we don't know anything about the algorithms here.
Calculates the weighted confidence score of a prediction
the prediction to score
the score keys to include in the calculation
the weights to influence the calculation
Generates an array of all possible alignment predictions
every possible n-gram in the source text
every possible n-gram in the target text
Generates an array of all possible contiguous n-grams within the sentence.
the tokens in a sentence
Returns an array of n-grams of a particular size from a sentence
the sentence from which n-grams will be read
the length of each n-gram.
Sorts an array of predictions by confidence
the predictions to sort
Sorts an array of suggestions by compound confidence
the suggestions to sort
Returns an array of alignment suggestions
a sorted array of predictions from which to base the suggestion
the maximum number of suggestions to return
forces suggestions to use words in order of occurrence. This may exponentially increase the processing time.
the minimum confidence a prediction must have to be used
Generated using TypeDoc
Represents a multi-lingual word alignment prediction engine.