Pytorch LSTM实例2

最新推荐文章于 2024-09-18 12:21:11 发布

csdn_1HAO

最新推荐文章于 2024-09-18 12:21:11 发布

阅读量609

点赞数

分类专栏： Pytorch

本文链接：https://blog.csdn.net/caomin1hao/article/details/106795747

版权

本文介绍了如何使用PyTorch中的LSTM进行词性标注，通过修改基本LSTM实例来实现这一任务。

摘要由CSDN通过智能技术生成

对Pytorch中LSTM实例稍作修改，这是一个词性标注的实例

#导入相应的包
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

torch.manual_seed(1)


#准备数据的阶段
def prepare_sequence(seq, to_ix):
    idxs = [to_ix[w] for w in seq]
    return torch.tensor(idxs, dtype=torch.long)

#DET 限定词， NN 名词 V 动词
training_data = [
    ("The dog ate the apple".split(), ["DET", "NN", "V", "DET", "NN"]),
    ("Everybody read that book".split(), ["NN", "V", "DET", "NN"])
]
word_to_ix = {}

for sent, tags in training_data:
    for word in sent:
        if word not in word_to_ix:
            word_to_ix[word] = len(word_to_ix)
print(word_to_ix)
#{'The': 0, 'dog': 1, 'ate': 2, 'the': 3, 'apple': 4, 'Everybody': 5, 'read': 6, 'that': 7, 'book': 8}
tag_to_ix = {"