应用人工智能从文本文档中提取知识的步骤 [英] Steps to apply artificial intelligence to extract knowledge from a text document
问题描述
我是人工智能领域的新手。我有一些关于模糊逻辑，人工神经网络，专家系统（基础架构）的基本（初级）知识。我对这些术语没有任何实际知识。
假设我的文件中有以下文字：
阿尔伯特爱因斯坦（1879年3月14日 - 1955年4月18日）是德国出生的理论物理学家。他发展了广义相对论，这是现代物理学的两大支柱之一（与量子力学一起）。爱因斯坦的工作也因其对科学哲学的影响而闻名。爱因斯坦因其质量能量等价公式E = mc2而在流行文化中最为人所知。[6]他因其理论物理服务获得了1921年诺贝尔物理学奖，特别是他发现了光电效应定律，量子理论发展的关键一步。
我试图从中解决这些问题：
1）阿尔伯特爱因斯坦是男人吗？ [提示：在通过中我们使用'他'，所以我们可以得出结论他是一个男人。]
2）阿尔伯特爱因斯坦活着吗？
3）列出爱因斯坦的成就？ [答案：他发明了能量质量方程;他获得了诺贝尔奖;发展广义相对论;光电效应定律]
4）这篇文章是在谈论什么？[答案：关于爱因斯坦]
I am very new to the Artificial Intelligence field. I have some basic( Beginner level) knowledge regarding fuzzy logic, Artificial Neural Network, Expert system (basic Architecture). I do not have any practical knowledge in these terms.
Suppose I have the following text in my document:
Albert Einstein (14 March 1879 – 18 April 1955) was a German-born theoretical physicist. He developed the general theory of relativity, one of the two pillars of modern physics (alongside quantum mechanics). Einsteins work is also known for its influence on the philosophy of science. Einstein is best known in popular culture for his mass–energy equivalence formula E = mc2 .[6] He received the 1921 Nobel Prize in Physics for his "services to theoretical physics", in particular his discovery of the law of the photoelectric effect, a pivotal step in the evolution of quantum theory.
I am trying to solve these questions from it:
1) Is Albert Einstein is Man? [Hint :in passage we are using 'He', so we can conclude that he is a man.]
2) Is Albert Einstein Alive ?
3) List the achievements of Albert Einstein? [Ans : He invented energy-mass equation; He won Nobel Prize; Developed General theory of relativity;law of the photoelectric effect]
4) What is this passage talking about?[Ans :About Albert Einstein]
My questions are :
- How to create Knowledge Base?
- What are the steps to attain this task?
- What is the role of NLP output for this task?
Any suggestions other than this is highly appreciated.
A lot of thanks in advance,
我尝试过的事情：
我已经阅读过使用混合系统可以制作的地方。即AI中许多系统的组合（ANN +模糊+等......）。
我也尝试过Stanford NLP，NLTK，Syntaxnet。他们提供解析输出。
What I have tried:
I have read somewhere that its possible to make using 'Hybrid system'. i.e combination of many systems in AI (ANN+Fuzzy+ etc...).
I have also tried Stanford NLP, NLTK, Syntaxnet. They are providing parsed output.
推荐答案
您的问题涉及自然语言理解，这是AI中最复杂的主题之一。我现在还不确定这样的事情是否存在。您可以找到一些或多或少成功的尝试，但它们并非一般用途，它们专门用于小型域。
它涉及一个绝对庞大的知识库。
自然语言理解 - 维基百科，免费的百科全书 [ ^ ]
Your question involve natural language understanding, which is one of the most complicated subjects in AI. I am not even sure such a thing exist at this time. You can find some attempts that are more or less successful, but they arz not general purpose, they are specialized on a small domain.
It involve an absolutely huge knowledge database.
Natural language understanding - Wikipedia, the free encyclopedia[^]
他发明了能量质量方程式
He invented energy-mass equation
没有没有发明方程式，他发现了这个方程，因为这个方程式早在发现之前就已经在使用了。
No did not invent the equation, he discovered this equation because the equation was already in use long before its discovery.
这篇关于应用人工智能从文本文档中提取知识的步骤的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
