Word Embedding¶
WordEmbedding is a tf.keras.layers.Embedding
layer with pre-trained Word2Vec/GloVe Emedding weights.
-
kashgari.embeddings.WordEmbedding.
__init__
(self, w2v_path: str, *, w2v_kwargs: Dict[str, Any] = None, **kwargs)¶ Parameters: - w2v_path – Word2Vec file path.
- w2v_kwargs – params pass to the
load_word2vec_format()
function of gensim.models.KeyedVectors - kwargs – additional params