def __init__(self):
self.wordvec = './model/wordvec.txt'
self.wordfreq = './model/wordfreq.txt'
self.params_ = params.params(1)
self.words = None
self.We = None
self.weight4ind = None
self.pc = None
def embeding_sentence_cosine_similarity(s1,s2):
word_idx_seq_of_sentence, mask = data_io.sentences2idx([s1,s2], Word2Indx) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
print(s1,s2)
print('word_idx_seq_of_sentence')
print(word_idx_seq_of_sentence)
print('mask')
print(mask)
word_weight_of_sentence = data_io.seq2weight(word_idx_seq_of_sentence, mask, Index2Weight) # get word weights
# set parameters
param = params.params()
param.rmpc = rmpc
embedding = SIF_embedding.SIF_embedding(Word2vector, word_idx_seq_of_sentence, word_weight_of_sentence, param)
s1_embed = embedding[0]
s2_embed = embedding[1]
return distance.cosine(s1_embed,s2_embed)
def cosine_distance_by_sentence_vector(s1, s2):
word_idx_seq_of_sentence, mask = data_io.sentences2idx(
[' '.join(s1), ' '.join(s2)], Word2Indx
) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
word_weight_of_sentence = data_io.seq2weight(
word_idx_seq_of_sentence, mask, Index2Weight) # get word weights
# set parameters
param = params.params()
param.rmpc = rmpc
embedding = SIF_embedding.SIF_embedding(Word2vector,
word_idx_seq_of_sentence,
word_weight_of_sentence, param)
s1_embed = embedding[0]
s2_embed = embedding[1]
return cosine_similarity(s1_embed, s2_embed)
parser.add_argument("-task", help="Either sim, ent, or sentiment.")
parser.add_argument(
"-weightfile",
help=
"The file containing the weights for words; used in weighted_proj_model_sim."
)
parser.add_argument("-weightpara",
help="The parameter a used in computing word weights.",
type=float)
parser.add_argument("-npc",
help="The number of principal components to use.",
type=int,
default=0)
args = parser.parse_args()
params = params()
params.LW = args.LW
params.LC = args.LC
params.batchsize = args.batchsize
params.hiddensize = args.dim
params.memsize = args.memsize
params.wordfile = args.wordfile
params.nntype = args.nntype
params.layersize = args.layersize
params.updatewords = str2bool(args.updatewords)
params.traindata = args.traindata
params.devdata = args.devdata
params.testdata = args.testdata
params.nntype = args.nntype
params.epochs = args.epochs
params.learner = learner2bool(args.learner)
# input
wordfile = '../data/glove.840B.300d.txt' # word vector file, can be downloaded from GloVe website
weightfile = '../auxiliary_data/enwiki_vocab_min200.txt' # each line is a word and its frequency
weightpara = 1e-3 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
rmpc = 1 # number of principal components to remove in SIF weighting scheme
sentences = [
'this is an example sentence',
'this is another sentence that is slightly longer'
]
# load word vectors
(words, We) = data_io.getWordmap(wordfile)
# load word weights
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
# load sentences
x, m = data_io.sentences2idx(
sentences, words
) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
w = data_io.seq2weight(x, m, weight4ind) # get word weights
# set parameters
params = params.params()
params.rmpc = rmpc
# get SIF embedding
embedding = SIF_embedding.SIF_embedding(
We, x, w, params) # embedding[i,:] is the embedding for sentence i