NLP（十三）：word2vec和siamese-LSTM结合计算文本相似度.pdfVIP

NLP （⼗三）：word2vec和siamese-LSTM结合计算⽂本相似度⼀、定义数据加载 my_dataset.py import torch.utils.data as data class MyDataset(data.Dataset): def__init__(self, texta, textb, label): self.texta = texta self.textb = textb self.label = label def__getitem__(self, item): texta = self.texta[item] textb = self.textb[item] label = self.label[item] return texta, textb, label def__len__(self): return len(self.texta) ⼆、定义词嵌⼊ my_word2vec.py from gensim.models.fasttext import FastText import torch import numpy as np import os class WordEmbedding(object): def__init__(self): parent_path = os.path.s