What chemistry can teach us about designing better NLP algorithms
The main idea behind this talk is how context is formed in language and how location, time, and order of words also has an effect on it.
Machine Learning, Artificial Intelligence and Automated Natural Language Analyses present some of the most interesting challenges for next generation computing. And as much as we’d like to believe otherwise, we are still a long way from developing bots that understand the universe of human language.
It isn't an easy problem because the idiosyncrasies of our language present certain difficulties for the systematic and logical brain of the machine. For instance, the meaning of a word can change based on the context.
The group has achieved fair and equal representation for all its members.
She is very fair with blue eyes.
Now it's very easy for the human eye to discern what the intent is, but how will the computer?
In this talk I am going to explain how natural language processing (NLP) can learn from chemistry in designing smarter engines. Yes, the chemistry of organic bonds and covalent bonds.
I will first show how chemistry and NLP are related and how chemical reactions and element knowledge can help us in NLP. Following this, I will compare periodic table elements in chemistry to NLP entities. There are very interesting linkages between radio active elements, isotopes in chemistry similar to words, places and meaning in the semantic world.
Participants should have a basic knowledge of natural language concepts.
Siva is a developer with Compile, where he works on practical applications for NLP algorithms.