tvecs.bilingual_generator package¶

Submodules¶

tvecs.bilingual_generator.bilingual_generator module¶

Module used to generate bilingual dictionary.

tvecs.bilingual_generator.bilingual_generator.build_sparse_bilingual_dictionary(bilingual_dictionary_path, model, encoding='utf-8', output_path='data/bilingual_dictionary', output_fname='sparse_bd', topn=5000, sample_size=1)[source]¶

Create Sparse Bilingual Dictionary.

Cluster pre-existing Bilingual Dictionary and sample from the same.

API Documentation

param bilingual_dictionary_path: Path for Bilingual Dictionary.
param model: Word2Vec Model for obtaining vectors.
param encoding: Encoding of the bilingual dictionary.
param output_fname: Output Filename for sparse bilingual dictionary.
param output_path: Output file path for bilingual dictionary.
param topn: Number of words considered from bilingual dictionary.
param sample_size: Number of samples from each cluster.
type bilingual_dictionary_path: String
type encoding: String
type model: ‘mod’gensim.models.Word2Vec.
type output_fname: String
type output_path: String
type topn: Integer
type sample_size: Integer

tvecs.bilingual_generator.cluster module¶

Test.

tvecs.bilingual_generator.cluster.build_clusters(entire_word_list, model, damping_factor=0.5)[source]¶

Cluster word_list using Affinity Propagation.

Clustering based on the vectors from the Word2Vec model.

API Documentation:

param entire_word_list: Word List provided to cluster.
param model: Model to obtain the vectors for the word_list.
param damping_factor: Damping factor for the affinity propagation.
type entire_word_list: List
type model: gensim.models.Word2Vec
type damping_factor: Float

tvecs.bilingual_generator.cluster.write_clusters(word_list, model, encoding='utf-8', output_path='.', output_fname='clusters.json')[source]¶

Write Clusters to the specified file as JSON.