Subscribe to our Newsletter

Unleashing Intelligence through natural language (Part 2 - Autonomously generated conclusions)

In this series I reveal rules of intelligence contained within grammar, and explain how they can be utilized to unleash intelligence in software. These rules are extremely simple, but still undiscovered by scientists.

Under certain conditions, three types of conclusions that can be generated autonomously:


1) Specification substitution conclusion:
• Given "John is a father" and "A father is a man";
• Because of the common word "father", a conclusion can be drawn: "John is a man" by substitution of both sentences.

(More detailed conditions: http://mafait.org/en/theory_2_3_1/)


2) Compound specification substitution conclusion:
• Given "A parent is a father or (a) mother", "A father is a man" and "A mother is a woman";
• Because of the common words "father" and "mother", a conclusion can be drawn: "A parent is a father or (a) mother", by substitution of those three sentences.

Another example:
• Given "Pete is a child (of John)" and "A child is a son or (a) daughter";
• Conclusion: "Pete is a son or (a) daughter (of John)".

In this conclusion the conjunction "or" is used, which indicates a choice (see Part 1). So, let's utilize this rule of intelligence, by converting the conclusion into a question, in order to stimulate the user to complement the knowledge: "Is Pete a son, or a daughter (of John)?".

(More detailed conditions: http://mafait.org/en/theory_2_3_1_1/)


3) Possessive reversible conclusion:
• Given "John is the father of Pete";
• Obvious conclusion by reversing the sentence and changing the verb: "Pete has a father (named John)".

(More detailed conditions: http://mafait.org/en/theory_2_3_2/)


To download the open source implementation: http://mafait.org/en/download/

Views: 467

Tags: Artificial, Business, Intelligence, Language, Natural, Processing, Rules

Comment

You need to be a member of BigDataNews to add comments!

Join BigDataNews

On Data Science Central

© 2019   BigDataNews.com is a subsidiary of DataScienceCentral LLC and not affiliated with Systap   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service