Follow project on Twitter

2.2.1. Deep-learning networks applied to natural language

Deep-learning networks are able to recognize and to produce patterns of a language. But they are unable to grasp the meaning expressed by humans through natural language, because natural language is like algebra and programming languages: It has “variables” (keywords) and “functions” (structure words).

In natural language, keywords – mainly nouns and proper nouns – provide the knowledge, while the logical structure of sentences is provided by words like definite article “the”, conjunction “or”, basic verb “is/are”, possessive verb “has/have” and past tense verbs “was/were” and “had”.

However, deep-learning networks are not hard-wired to process logic. So, this technique is unable to process the logic that is embedded in natural language. And therefore, this technique is unable to grasp the deeper meaning expressed by humans through natural language.

Deep-learning networks are based on pattern recognition. And therefore, they are limited to perform tasks based on pattern recognition.

Thinknowlogy 2018r3

will be published in November this year. It will contain part 4 of an internal redesign. See my planning for the other planned publications. Follow this project on Twitter, subscribe to project updates on SourceForge, subscribe to project updates on GitHub or receive an email when a new version is available.

Join my Fair Science Supporters group on LinkedIn to support a fair practice of science, and/or my Fair Science • Artificial Intelligence (AI) and knowledge technology (NLP) group, which is dedicated to a fair practice of Artificial Intelligence and knowledge technology. Or send me a LinkedIn invitation.

God has created laws of nature to make his creation run like clockwork. It includes: Natural Laws of Intelligence embedded in Grammar. Thinknowlogy implements these natural laws of intelligence in software.