用少量的学习来提取实体
现在我们将进行实体提取，这要归功于少许的学习。
比方说，你想从网站上提取职位名称。在提出你的实际要求之前，只需给出几个职位名称提取的例子。
Extract job titles from the following sentences.
Sentence: John Doe has been working for Microsoft for 20 years as a Linux Engineer.
Job title: Linux Engineer
###
Sentence: John Doe has been working for Microsoft for 20 years and he loved it.
Job title: none
###
Sentence: Marc Simoncini | Director | Meetic
Job title: Director
###
Sentence: Franck Riboud was born on 7 November 1955 in Lyon. He is the son of Antoine Riboud, who transformed the former European glassmaker BSN Group into a leading player in the food industry. He is the CEO at Danone.
Job title: CEO
###
Sentence: Damien is the CTO of Platform.sh, he was previously the CTO of Commerce Guys, a leading ecommerce provider.
Job title:
其结果将是如下。
Extract job titles from the following sentences.
Sentence: John Doe has been working for Microsoft for 20 years as a Linux Engineer.
Job title: Linux Engineer
###
Sentence: John Doe has been working for Microsoft for 20 years and he loved it.
Job title: none
###
Sentence: Marc Simoncini | Director | Meetic
Job title: Director
###
Sentence: Franck Riboud was born on 7 November 1955 in Lyon. He is the son of Antoine Riboud, who transformed the former European glassmaker BSN Group into a leading player in the food industry. He is the CEO at Danone.
Job title: CEO
###
Sentence: Damien is the CTO of Platform.sh, he was previously the CTO of Commerce Guys, a leading ecommerce provider.
Job title: CTO
正如你所注意到的，我们必须对如何制作我们的少数几个例子采取明智的态度。可能发生的情况是，根本没有找到任何职位，这就是为什么我们创建了一个返回 "无 "的例子（它避免了假阳性）。也许你想同时提取几个职位名称？在这种情况下，创建返回几个职位名称的例子也很重要（例如，逗号分隔的职位名称）。
通过增加更多的例子，你会得到更好的结果。而且重要的是，你的例子要尽可能地接近你的实际最终要求。例如，如果你知道你要分析的是整个段落而不是单纯的句子，那么最好也要创建有段落的例子。
如果你没有访问GPT模型，你可以简单地使用NLP Cloud API。有几个客户端可用（Python、Go、Node.js、Ruby、PHP...）。让我们在这里展示一个使用GPT-J与Python客户端的例子。
import nlpcloud
client = nlpcloud.Client("gpt-j", "your API token", gpu=True)
client.generation("""Extract job titles from the following sentences.
Sentence: John Doe has been working for Microsoft for 20 years as a Linux Engineer.
Job title: Linux Engineer
###
Sentence: John Doe has been working for Microsoft for 20 years and he loved it.
Job title: none
###
Sentence: Marc Simoncini | Director | Meetic
Job title: Director
###
Sentence: Franck Riboud was born on 7 November 1955 in Lyon. He is the son of Antoine Riboud, who transformed the former European glassmaker BSN Group into a leading player in the food industry. He is the CEO at Danone.
Job title: CEO
###
Sentence: Damien is the CTO of Platform.sh, he was previously the CTO of Commerce Guys, a leading ecommerce provider.
Job title:""",
top_p=0.1,
length_no_input=True,
remove_input=True,
end_sequence="###",
remove_end_sequence=True
)
其结果将是。 CTO
让我给你简单解释一下我们刚才使用的文本生成参数。
我们设置了一个非常低的最高P值，因为我们不希望GPT-J创造出太原始的结果：我们只希望它坚持在你的请求中看到的东西。
"length_no_input "表示最大长度值不应该考虑到输入的文本。
"remove_input "表示应该从结果中删除输入的文本。
"end_sequence "意味着当模型遇到这个字符时，它应该停止生成文本。正如在我们的几张照片的例子中，我们在每个答案的末尾添加了 "##"，模型在生成反应后会自动生成 "##"，并且会在那里停止。
"remove_end_sequence "意味着我们要从响应中删除 "##"。
你可以在NLP Cloud文档中看到更多细节。 在这里看到。
注释性插图