Infersent1_setup.py

! mkdir encoder
! curl -Lo encoder/infersent2.pkl https://dl.fbaipublicfiles.com/infersent/infersent2.pkl
  
! mkdir GloVe
! curl -Lo GloVe/glove.840B.300d.zip http://nlp.stanford.edu/data/glove.840B.300d.zip
! unzip GloVe/glove.840B.300d.zip -d GloVe/

InferSent2_loadmodel.py

from models import InferSent
import torch

V = 2
MODEL_PATH = 'encoder/infersent%s.pkl' % V
params_model = {'bsize': 64, 'word_emb_dim': 300, 'enc_lstm_dim': 2048,
                'pool_type': 'max', 'dpout_model': 0.0, 'version': V}
model = InferSent(params_model)
model.load_state_dict(torch.load(MODEL_PATH))

W2V_PATH = '/content/GloVe/glove.840B.300d.txt'
model.set_w2v_path(W2V_PATH)

InferSent3_buildvocab.py

model.build_vocab(sentences, tokenize=True)

InferSent4_encode.py

query = "I had pizza and pasta"
query_vec = model.encode(query)[0]
query_vec

InferSent5_compute.py

similarity = []
for sent in sentences:
  sim = cosine(query_vec, model.encode([sent])[0])
  print("Sentence = ", sent, "; similarity = ", sim)