Let’s talk about language
We use natural language as an everyday means to communicate with other humans, through our innate ability to understand, process and utilize words. English, French, Spanish, and the list continues. All languages have a syntax and grammar, and comply with the principles of economy and optimality, although there are sometimes ambiguities.
Since the first language, Sanskrit, languages have evolved together with humankind, yet no particular human has created any natural language. Although each language has unique rules and structure, they are very different from artificially created ones (called ‘constructed languages), like computer programming languages.
Helping computers understand humans
Oppositely, formal languages are those used to transfer information, where no ambiguity is possible. The math notations PHP, SQL and XML are examples of these, with which computers can work very efficiently. At the same time, one of the biggest challenges in computer science is the creation of computers which are able to understand natural language. For that purpose, there is a whole field within computer science concerned with the interactions between computers and human (natural) languages — artificial intelligence.
The heart of Inbenta is NLP
Because natural languages have not been ‘designed’ in the same way that formal languages are, they tend to have many ambiguities. The same word, phrase or even an entire sentence can have multiple meanings, and one concept may be expressed in multiple different ways. This means that natural language is very expressive, yet also that there can be confusion and varied interpretations.
Inbenta has natural language processing, or NLP technology, at its core. Theoretical linguistic frameworks like the meaning-text theory (MTT) — used for constructing of models of natural language — allow computers, and thus your search technology to process natural language by understanding the meaning behind the words.
NLP technology and semantic search
Thanks to NLP theoretical frameworks and computer models led by MTT, we’ve been able to create the semantic search engine, which allows your users to efficiently search for complex information, even if what’s typed are incomplete, ambiguous, unstructured questions in their native language.