manhobby wrote:
Why are there not a place to Start for People Interested in Natural Language Programming?
You could try setting up a Facebook group for that to see if there's enough interest in the idea to justify a proper forum, but I don't think many people working in the field will be keen to give a lot of information away because it could be equivalent to handing hundreds of billions of dollars to their rivals, and they aren't that crazy. It would also aid the development of intelligent killer robots for use on the battlefield, and that's another reason why a lot of the details should not be shared openly (until the more moral countries have built up an overwhelming lead in that area). It's a very different situation with OS development because there are plenty of parts that are freely available and well documented, so anyone who wants to have a go can simply collect the necessary parts and build an OS out of them.
If you want to build a system for natural language programming, you're really going to have to work most of it out for yourself. Gerry has revealed how his system works, but it isn't natural language programming. I pointed you towards it because it's a good starting point for seeing how a simple approach can achieve a lot more than might be expected, but it's also an opportunity to see the places where it fails, and that helps you see where the problems are that you would need to solve to get to real NLP. Gerry thinks that as more and more lines of code are added to his system (to cover more and more relationships between actions and things) it will appear more and more intelligent, eventually reaching the point where it looks fully intelligent and understands practically all possible wordings that might be used as instructions such that it responds to them correctly. He thinks that the personal digital assistants built by Amazon, Google, Apple, etc. are working in much the same way, but they have millions of users helping to train them, effectively building millions of lines of code to handle more and more specific phrases. His PEP system can't compete with that due to its small number of users. But it isn't the right approach anyway - it will never produce sufficient intelligence to be fully rational.
If you want a rational system that can handle all phrases, you can't cheat - you have to understand the entire process mechanistically and program every single part of it, converting from surface level language down into the structure of thought (and you need to be able to convert to full depth where you're working with the fundamental components of meaning), and you also have to find the right ways to store the data so that reasoning can be applied to it efficiently. There are no shortcuts - it's takes decades of hard thinking and it eats up your life, which is why people prefer to look for easier options. The details of the easier options have been published because they only half work, but they will continue to improve, so if you want a forum to discuss that, go ahead and set one up.
Quote:
Maybe also instead of using the high-level languages, programmers will start using human language level programming.
What is OS Dev.org Community's opinion about human language level programming?
I'm sure they will adapt to it in a hurry when it's available, but it isn't yet and won't be of a lot of interest to them until it is. You aren't going to learn anything by asking the same people the same questions again and again.