Bengali Word2Vec Model

Datasets

• Wikipedia dump datasets

Training details

• Word2Vec word embedding dimension = 100, min_count=5, window=5, epochs=10

Usage

• pip install -U bengalinlp_toolkit
• Generate Vector using pretrain model
  py

  1from bengalinlp import BengaliWord2Vec 2 3bwv = BengaliWord2Vec() 4model_path = "bengali_word2vec.model" 5word = 'গ্রাম' 6vector = bwv.generate_word_vector(model_path, word) 7print(vector.shape) 8print(vector) 9
• Find Most Similar Word Using Pretrained Model
  py

  1from bengalinlp import BengaliWord2Vec 2 3bwv = BengaliWord2Vec() 4model_path = "bengali_word2vec.model" 5word = 'গ্রাম' 6similar = bwv.most_similar(model_path, word, topn=10) 7print(similar) 8