I had read some blogs (like 1, 2 or 3) about what the difference between all three of them is. I am trying to build an open domain conversation agent using natural language AI. That agent can do casual conversation, like a friend. So, for that, I want to know what is the importance of NLP, NLG, and NLU, so that I can learn that part first.
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
They're all important. NLP is an umbrella term that includes the other two; NLG is only concerned with generating language, ie transforming some internal data structure into human language. NLU is about processing information contained in language, and putting it into relation with a knowledge base etc.
If you don't know anything about any of these fields, then I suggest your aim is far too optimistic. I work for a company that provides a conversational AI platform for businesses to develop their own agents, and it is a complex area.
If you want to have a quick go and pick up some experience, I suggest you start with ELIZA. Even though this is 'ancient', many modern chatbots still work on the same principles. There are many implementations in a number of programming languages, so you should be able to find one that suits you and you can tinker around with it.
