Last active
March 10, 2017 19:06
-
-
Save bwang482/a4b2de9b5037d9ad69fa82da6ae67641 to your computer and use it in GitHub Desktop.
Sentence embedding method in [Arora et al. ICLR 2017] - https://openreview.net/pdf?id=SyK00v5xx
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from __future__ import division | |
import gensim | |
import itertools | |
import numpy as np | |
from collections import Counter | |
from sklearn.decomposition import PCA | |
def gensim_load_vec(path): | |
w2v_model = gensim.models.Word2Vec.load_word2vec_format(path, binary=False) | |
shape = gensim_emb.syn0.shape | |
return w2v_model, shape | |
def map_word_frequency(document): | |
return Counter(itertools.chain(*document)) | |
def sentence2vec(tokenised_sentence_list, embedding_size, word_emb_model, a = 1e-3): | |
""" | |
Computing weighted average of the word vectors in the sentence; | |
remove the projection of the average vectors on their first principal component. | |
Borrowed from https://github.com/peter3125/sentence2vec; now compatible with python 2.7 | |
""" | |
word_counts = map_word_frequency(tokenised_sentence_list) | |
sentence_set=[] | |
for sentence in tokenised_sentence_list: | |
vs = np.zeros(embedding_size) | |
sentence_length = len(sentence) | |
for word in sentence: | |
a_value = a / (a + word_counts[word]) # smooth inverse frequency, SIF | |
try: | |
vs = np.add(vs, np.multiply(a_value, word_emb_model[word])) # vs += sif * word_vector | |
except: | |
pass | |
vs = np.divide(vs, sentence_length) # weighted average | |
sentence_set.append(vs) | |
# calculate PCA of this sentence set | |
pca = PCA(n_components=embedding_size) | |
pca.fit(np.array(sentence_set)) | |
u = pca.explained_variance_ratio_ # the PCA vector | |
u = np.multiply(u, np.transpose(u)) # u x uT | |
if len(u) < embedding_size: | |
for i in range(embedding_size - len(u)): | |
u = np.append(u, 0) # add needed extension for multiplication below | |
# resulting sentence vectors, vs = vs - u x uT x vs | |
sentence_vecs = [] | |
for vs in sentence_set: | |
sub = np.multiply(u,vs) | |
sentence_vecs.append(np.subtract(vs, sub)) | |
return sentence_vecs | |
# yo | |
w2v_model, glove_shape = gensim_load_vec('../glove.twitter.word2vec.27B.100d.txt') | |
tweets = ['It was all a dream', 'I used to read Word Up magazine'] | |
tweets = [tweet.split() for tweet in tweets] | |
embedding_size = glove_shape[1] | |
sent_emb = sentence2vec(tweets, embedding_size, w2v_model) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment