How to train new SRL model ? about polyglot HOT 1 CLOSED

Hi, @GraphGrail ,
To use the pre-trained word embeddings from Polyglot in your project, you can download and load it using Polyglot's Embedding class. The following examples assume that you have installed Polyglot as mentioned in https://polyglot.readthedocs.org/en/latest/Installation.html

Taking English (whose language code is en) as example, to download you may use the following Bash commands:

lang='en'
polyglot download embeddings2.${lang}

And to use it in your project, you may use the following Python snip:

from os import path

from polyglot.mapping import Embedding

lang = 'en'
home = path.expanduser('~')
emb = Embedding.load(path.join(home, 'polyglot_data/embeddings2/%s/embeddings_pkl.tar.bz2' % lang))
words = emb.words
vectors = emb.vectors

And now you can play with words, which is a list of strings representing the vocabulary, and vectors, which is a 2-d NumPy array whose i-th row (vectors[i]) is the word embedding for the i-th word in words.

from polyglot.