Skip to content
Pre-trained Embedding for VLSP2019-HSD Task
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
README.md
dict_map_comment.pkl

README.md

[VLSP2019-Hate Speech Detection Task] Register for using pre-trained embeddings

Text for train embedding

  • Data from HSD task
  • Data crawl from social network (Facebook)

Type word embedding

  • CBOW word
  • CBOW BPE word piece
  • Roberta

Load word2vec using pickle

import pickle

w2v_dict = pickle.load(open('./dict_map_comment.pkl', 'rb'))
print(w2v_dict['comment']['hello'].shape)
# (200,)
print(w2v_dict['comment_bpe']['hello'].shape)
# (200,)
You can’t perform that action at this time.