昇思25天学习打卡营第25天|文本解码原理--以MindNLP为例

最新推荐文章于 2024-08-28 18:49:37 发布

Phantom934

最新推荐文章于 2024-08-28 18:49:37 发布

阅读量662

点赞数 31

文章标签：学习 android

本文链接：https://blog.csdn.net/qq_45459104/article/details/140673524

版权

提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档

文章目录

回顾：自回归语言模型
- Greedy search
一、环境准备
二、具体代码
总结与感想

回顾：自回归语言模型

根据前文预测下一个单词

一个文本序列的概率分布可以分解为每个词基于其上文的条件概率的乘积

𝑊_0:初始上下文单词序列
𝑇: 时间步
当生成EOS标签时，停止生成。

MindNLP/huggingface Transformers提供的文本生成方法

Greedy search

在每个时间步𝑡都简单地选择概率最高的词作为当前输出词:

𝑤_𝑡=𝑎𝑟𝑔𝑚𝑎𝑥_𝑤 𝑃(𝑤|𝑤_(1:𝑡−1))

按照贪心搜索输出序列(“The”,“nice”,“woman”) 的条件概率为：0.5 x 0.4 = 0.2

缺点: 错过了隐藏在低概率词后面的高概率词，如：dog=0.5, has=0.9

一、环境准备

%%capture captured_output
# 实验环境已经预装了mindspore==2.2.14，如需更换mindspore版本，可更改下面mindspore的版本号
!pip uninstall mindspore -y
!pip install -i https://pypi.mirrors.ustc.edu.cn/simple mindspore==2.2.14

!pip uninstall mindvision -y
!pip uninstall mindinsight -y

!pip install mindnlp

#greedy_search

from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')

# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')

# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')

# generate text until the output length (which includes the context length) reaches 50
greedy_output = model.generate(input_ids, max_length=50)

print("Output:\n" + 100 * '-')
print(tokenizer.decode(greedy_output[0], skip_special_tokens=True))

输出为：
在这里插入图片描述

二、具体代码

Beam search

Beam search通过在每个时间步保留最可能的 num_beams 个词，并从中最终选择出概率最高的序列来降低丢失潜在的高概率序列的风险。如图以 num_beams=2 为例:

(“The”,“dog”,“has”) : 0.4 * 0.9 = 0.36

(“The”,“nice”,“woman”) : 0.5 * 0.4 = 0.20

优点：一定程度保留最优路径

缺点：1. 无法解决重复问题；2. 开放域生成效果差

在这里插入图片描述

from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')

# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')

# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')

# activate beam search and early_stopping
beam_output = model.generate(
    input_ids, 
    max_length=50, 
    num_beams=5, 
    early_stopping=True
)

print("Output:\n" + 100 * '-')
print(tokenizer.decode(beam_output[0], skip_special_tokens=True))
print(100 * '-')

# set no_repeat_ngram_size to 2
beam_output = model.generate(
    input_ids, 
    max_length=50, 
    num_beams=5, 
    no_repeat_ngram_size=2, 
    early_stopping=True
)

print("Beam search with ngram, Output:\n" + 100 * '-')
print(tokenizer.decode(beam_output[0], skip_special_tokens=True))
print(100 * '-')

# set return_num_sequences > 1
beam_outputs = model.generate(
    input_ids, 
    max_length=50, 
    num_beams=5, 
    no_repeat_ngram_size=2, 
    num_return_sequences=5, 
    early_stopping=True
)

# now we have 3 output sequences
print("return_num_sequences, Output:\n" + 100 * '-')
for i, beam_output in enumerate(beam_outputs):
    print("{}: {}".format(i, tokenizer.decode(beam_output, skip_special_tokens=True)))
print(100 * '-')

输出为：

Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again."

"I don't think I'll ever be able to walk with her again."

"I don't think I
----------------------------------------------------------------------------------------------------
Beam search with ngram, Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again."

"I'm not sure what to say to that," she said. "I mean, it's not like I'm
----------------------------------------------------------------------------------------------------
return_num_sequences, Output:
----------------------------------------------------------------------------------------------------
0: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again."

"I'm not sure what to say to that," she said. "I mean, it's not like I'm
1: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again."

"I'm not sure what to say to that," she said. "I mean, it's not like she's
2: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again."

"I'm not sure what to say to that," she said. "I mean, it's not like we're
3: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again."

"I'm not sure what to say to that," she said. "I mean, it's not like I've
4: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again."

"I'm not sure what to say to that," she said. "I mean, it's not like I can
----------------------------------------------------------------------------------------------------

Beam search issues

在这里插入图片描述

缺点：1. 无法解决重复问题；2. 开放域生成效果差

Repeat problem

在这里插入图片描述

n-gram 惩罚:

将出现过的候选词的概率设置为 0

设置no_repeat_ngram_size=2 ，任意 2-gram 不会出现两次

Notice: 实际文本生成需要重复出现

Sample

根据当前条件概率分布随机选择输出词𝑤_𝑡
在这里插入图片描述

优点：文本生成多样性高

缺点：生成文本不连续

import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')

# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')

# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')

mindspore.set_seed(0)
# activate sampling and deactivate top_k by setting top_k sampling to 0
sample_output = model.generate(
    input_ids, 
    do_sample=True, 
    max_length=50, 
    top_k=0
)

print("Output:\n" + 100 * '-')
print(tokenizer.decode(sample_output[0], skip_special_tokens=True))

Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog Neddy as much as I'd like. Keep up the good work Neddy!"

I realized what Neddy meant when he first launched the website. "Thank you so much for joining."

I

Temperature

降低softmax 的temperature使 P(w∣w1:t−1)分布更陡峭
在这里插入图片描述

增加高概率单词的似然并降低低概率单词的似然

import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')

# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')

# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')

mindspore.set_seed(1234)
# activate sampling and deactivate top_k by setting top_k sampling to 0
sample_output = model.generate(
    input_ids, 
    do_sample=True, 
    max_length=50, 
    top_k=0,
    temperature=0.7
)

print("Output:\n" + 100 * '-')
print(tokenizer.decode(sample_output[0], skip_special_tokens=True))

Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog and have never had a problem with her until now.

A large dog named Chucky managed to get a few long stretches of grass on her back and ran around with it for about 5 minutes, ran around

TopK sample

选出概率最大的 K 个词，重新归一化，最后在归一化后的 K 个词中采样

在这里插入图片描述

TopK sample problems

在这里插入图片描述

将采样池限制为固定大小 K ：

在分布比较尖锐的时候产生胡言乱语
在分布比较平坦的时候限制模型的创造力

import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')

# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')

# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')

mindspore.set_seed(0)
# activate sampling and deactivate top_k by setting top_k sampling to 0
sample_output = model.generate(
    input_ids, 
    do_sample=True, 
    max_length=50, 
    top_k=50
)

print("Output:\n" + 100 * '-')
print(tokenizer.decode(sample_output[0], skip_special_tokens=True))

Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog.

She's always up for some action, so I have seen her do some stuff with it.

Then there's the two of us.

The two of us I'm talking about were

Top-P sample

在累积概率超过概率 p 的最小单词集中进行采样，重新归一化
在这里插入图片描述

采样池可以根据下一个词的概率分布动态增加和减少

import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')

# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')

# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')

mindspore.set_seed(0)

# deactivate top_k sampling and sample only from 92% most likely words
sample_output = model.generate(
    input_ids, 
    do_sample=True, 
    max_length=50, 
    top_p=0.92, 
    top_k=0
)

print("Output:\n" + 100 * '-')
print(tokenizer.decode(sample_output[0], skip_special_tokens=True))

Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog Neddy as much as I'd like. Keep up the good work Neddy!"

I realized what Neddy meant when he first launched the website. "Thank you so much for joining."

I

top_k_top_p

import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')

# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')

# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')

mindspore.set_seed(0)
# set top_k = 50 and set top_p = 0.95 and num_return_sequences = 3
sample_outputs = model.generate(
    input_ids,
    do_sample=True,
    max_length=50,
    top_k=5,
    top_p=0.95,
    num_return_sequences=3
)

print("Output:\n" + 100 * '-')
for i, sample_output in enumerate(sample_outputs):
  print("{}: {}".format(i, tokenizer.decode(sample_output, skip_special_tokens=True)))

Output:
----------------------------------------------------------------------------------------------------
0: I enjoy walking with my cute dog.

"My dog loves the smell of the dog. I'm so happy that she's happy with me.

"I love to walk with my dog. I'm so happy that she's happy
1: I enjoy walking with my cute dog. I'm a big fan of my cat and her dog, but I don't have the same enthusiasm for her. It's hard not to like her because it is my dog.

My husband, who
2: I enjoy walking with my cute dog, but I'm also not sure I would want my dog to walk alone with me."

She also told The Daily Beast that the dog is very protective.

"I think she's very protective of

总结与感想

今天学习了文本解码原理的相关知识。首先回顾了自回归语言模型的定义。自回归语言模型是一种基于概率的语言模型，它的主要目标是预测一个序列中的下一个词或字符。然后我学习了多种用于在生成文本时选择下一个词或字符的方法如Beam search，Sample，TopK sample等等和它们的优劣。现在只是初步了解，还需要进一步的学习。

Phantom934

关注

31
点赞
踩
22

收藏

觉得还不错? 一键收藏
0
评论
昇思25天学习打卡营第25天|文本解码原理--以MindNLP为例

今天学习了文本解码原理的相关知识。首先回顾了自回归语言模型的定义。自回归语言模型是一种基于概率的语言模型，它的主要目标是预测一个序列中的下一个词或字符。然后我学习了多种用于在生成文本时选择下一个词或字符的方法如Beam search，Sample，TopK sample等等和它们的优劣。现在只是初步了解，还需要进一步的学习。
复制链接

扫一扫