Semantic development definition in the case of humans vs. machines
Semantic development definition: How humans learn
When we talk about human capabilities for learning, it’s easy to understand how (A semantic development definition that I like refers to it as a “gradual process of acquiring the meanings associated with words”). When a child hears a word for the first time, he tries to understand the meaning using past experience, intellect, memory, etc. Children of up to one year old know the meaning of 50 to 100 words and their vocabulary grows rapidly from there. At five years of age, children can use about 2,000 words.
Semantic development definition: How the machines learn
But how can we define semantic development when it comes to machines and not people?
For People, learning is a life long process. Humans have innate and intuitive capabilities that allow them to understand the meaning of words based on a variety of elements such as experience, memory, etc. A machine, however, does not have such a reference system to support it in this process of acquiring knowledge.
So how do machines learn? To be able to acquire knowledge, machines need a system that provides access to background information, and that allows them to cope with text ambiguities and meaning recognition. Ideally, this is done in a way that is similar to how a human learns. Such a system, combined with the machine’s memory and computing capabilities, results in a powerful module capable of logical and comprehensive text understanding.
Our semantic development definition starts from a disambiguator and a knowledge graph
To identify a proper semantic development definition in the case of machines, we have to start from a different element. At Expert System, we call it the Semantic Disambiguator.
The semantic disambiguator is a linguistic software module that is able to solve ambiguities and understand the meaning of each word in a text. This is possible thanks to multi-level text analysis and the semantic disambiguator’s interaction with a representation of knowledge where concepts are connected to one other by specific semantic relationships. This is our Knowledge Graph.
When the disambiguator comes across a new word (the Knowledge Graph is incredibly rich but it doesn’t know everything, just as a human can’t know everything), it tries to figure out the meaning by considering the context. To do so, it applies complex algorithms and heuristic rules to use the known words surrounding the unknown element.
Like a human, Expert System semantic technology acquires knowledge and learns automatically and from human experience. And, thanks to this multilevel text analysis, semantic technology allows users to reach accuracy levels over 90% in totally open contexts in order to fully understand the meaning of single words, sentences and entire documents.