PyTorch单词嵌入
PyTorch单词嵌入详细操作教程
在本章中，我们将了解单词嵌入模型—word2vec。Word2vec模型用于在相关模型组的帮助下生成单词嵌入。Word2vec模型使用纯C代码实现，并且手动计算梯度。
PyTorch中word2vec模型的实现在以下步骤中解释 -
第1步
在以下库中实现单词嵌入，如下所述 -
# Filename : example.py
# Copyright : 2020 By Lidihuo
# Author by : www.lidihuo.com
# Date : 2020-08-23
import torch
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
第2步
使用名为word2vec的类实现单词嵌入的Skip Gram模型。它包括：emb_size，emb_dimension，u_embedding，v_embedding类型的属性。
# Filename : example.py
# Copyright : 2020 By Lidihuo
# Author by : www.lidihuo.com
# Date : 2020-08-23
class SkipGramModel(nn.Module):
def __init__(self, emb_size, emb_dimension):
super(SkipGramModel, self).__init__()
self.emb_size = emb_size
self.emb_dimension = emb_dimension
self.u_embeddings = nn.Embedding(emb_size, emb_dimension, sparse=True)
self.v_embeddings = nn.Embedding(emb_size, emb_dimension, sparse = True)
self.init_emb()
def init_emb(self):
initrange = 0.5 / self.emb_dimension
self.u_embeddings.weight.data.uniform_(-initrange, initrange)
self.v_embeddings.weight.data.uniform_(-0, 0)
def forward(self, pos_u, pos_v, neg_v):
emb_u = self.u_embeddings(pos_u)
emb_v = self.v_embeddings(pos_v)
score = torch.mul(emb_u, emb_v).squeeze()
score = torch.sum(score, dim = 1)
score = F.logsigmoid(score)
neg_emb_v = self.v_embeddings(neg_v)
neg_score = torch.bmm(neg_emb_v, emb_u.unsqueeze(2)).squeeze()
neg_score = F.logsigmoid(-1 * neg_score)
return -1 * (torch.sum(score)+torch.sum(neg_score))
def save_embedding(self, id2word, file_name, use_cuda):
if use_cuda:
embedding = self.u_embeddings.weight.cpu().data.numpy()
else:
embedding = self.u_embeddings.weight.data.numpy()
fout = open(file_name, 'w')
fout.write('%d %d' % (len(id2word), self.emb_dimension))
for wid, w in id2word.items():
e = embedding[wid]
e = ' '.join(map(lambda x: str(x), e))
fout.write('%s %s' % (w, e))
def test():
model = SkipGramModel(100, 100)
id2word = dict()
for i in range(100):
id2word[i] = str(i)
model.save_embedding(id2word)
第3步
实现main方法，以正确的方式显示单词嵌入模型。
# Filename : example.py
# Copyright : 2020 By Lidihuo
# Author by : www.lidihuo.com
# Date : 2020-08-23
if __name__ == '__main__':
test()
