|
COBOL was the first "natural language" programming language. Enough said!
- I would love to change the world, but they won’t give me the source code.
|
|
|
|
|
OriginalGriff wrote: ...I'm not convinced that natural language is a good idea for programming - it's too imprecise, too open to misinterpretation...
Just the absence of differentiation between Inclusive OR (IOR) and Exclusive OR (XOR) disqualifies natural language. That's a pretty basic concept that is completely absent.
I'm retired. There's a nap for that...
- Harvey
|
|
|
|
|
That's not a fault in natural language per se, more of a shortcoming in English (and possibly many other languages too). In fact the whole "too imprecise" problem is down to the "implementation" of natural language. Maybe we could, I dunno, create some sort of natural language, with its own syntax and structure, that computers could understand without ambiguity? oh... doh. 
|
|
|
|
|
I tend to think the opposite, natural language will become the way computers are programmed - we aren't there yet but it will come.
I agree that most natural language can be imprecise, but you can work around this by echoing back in plain english what we think you said in precise terms "Next friday" becomes "Friday the 9th of November". We replaced a very complex data entry screen with 50+ input fields and checkboxes and turned it to english input. End user mistakes have dropped, help desk calls have dropped. To be fair the english parser is super dumb, and we are only using it for very specific domains, not complete programs, but the power is evident. Small first steps, but I can see we could probably build a simple PWA based purely on english if that was our aim.
Heck, we even now have an experimental API that takes classic query parameters OR english /people?q=get 5 most recent seen with blue as favourite color. Vs /people?limit=5&order=recentseen&select=favouritecolor(blue)
I hate to say it, but it is putting power into end users who aren't programmers. Most end users can look intuitively at previous sentences and understand how to change it. Sure, it cannot handle all the nuances yet, and users learn to phrase in a certain way.
When you step right back, isn't a programming language simply another language like english/french/german? Programmers take natural language requirements and translate to C/Java/etc which compilers then translate again to machine code. Of course programmers [should] also have more logical thought patterns than J.Bloggs which is currently still required.
|
|
|
|
|
There were attempts during the 1950's and -60's to create Loglan, the first of a series of constructed, unambiguous languages that (presumably) humans and computers could share. The idea never really caught on, not even to the extent that Esperanto (another constructed language) has.
Apparently, humans do not like thinking logically. 
Freedom is the freedom to say that two plus two make four. If that is granted, all else follows.
-- 6079 Smith W.
|
|
|
|
|
Daniel Pfeffer wrote: Apparently, humans do not like can't thinking logically. (at least the big %) 
FTFY
M.D.V. 
If something has a solution... Why do we have to worry about?. If it has no solution... For what reason do we have to worry about?
Help me to understand what I'm saying, and I'll explain it better to you
Rating helpful answers is nice, but saying thanks can be even nicer.
|
|
|
|
|
Humans are not logical.
But we (most of us) are able to think logically, even though it takes a bit of effort for most people.
|
|
|
|
|
We are the exception confirming the rule 
M.D.V.
If something has a solution... Why do we have to worry about?. If it has no solution... For what reason do we have to worry about?
Help me to understand what I'm saying, and I'll explain it better to you
Rating helpful answers is nice, but saying thanks can be even nicer.
|
|
|
|
|
Not unless natural language will be replaced by something like Java or C# (I hope not JavaScript ).
|
|
|
|
|
Quantum Robin wrote: Just as most programmers today warn people not to use assembler, probably future programmers will warn people not to use anything other than natural language.
I think everyone should learn assembly!
Given how poorly people communicate with natural language, I think programming languages will be around for a while. We don't do very well with them either!
|
|
|
|
|
Ph'nglui mglw'nafh Osmosian R'lyeh wgah'nagl fhtagn. 
Did you ever see history portrayed as an old man with a wise brow and pulseless heart, weighing all things in the balance of reason?
Is not rather the genius of history like an eternal, imploring maiden, full of fire, with a burning heart and flaming soul, humanly warm and humanly beautiful?
--Zachris Topelius
Training a telescope on one’s own belly button will only reveal lint. You like that? You go right on staring at it. I prefer looking at galaxies.
-- Sarah Hoyt
|
|
|
|
|
This answer is the most underrated here. Have an upvote for the mix of Ctuhlu and the hidden reference to the PEC (I won't write in plain text to avoid making advertisement for it).
|
|
|
|
|
I reject the premise of the question.
|
|
|
|
|
Will future programmers probably warn people not to use high-level programming languages just as most programmers today warn people not to use assembler?
If yes, what are the programming languages that will replace the high-level programming languages?
|
|
|
|
|
Please see previous response.
|
|
|
|
|
There's a distinct possibility we will get to natural language programming. Many of the comments above say that people don't think logically, and that is true. They will not sit down and dictate the entire operation of an application from A to Z flawlessly on their first attempt. The process will be necessarily iterative. Something like this:
"Make a page that shows me my stock quotes and the weather."
"Put the weather in the top right."
"The weather should show the current temperature and the 24 hour forecast for my current location."
"For the stocks, show the current trading price for Microsoft and Bill's Sweat Socks from the TSE"
"Also show an up/down arrow for the four hour trend"
This will take some work, but I don't think we're too far away.
Outside of a dog, a book is a man's best friend; inside of a dog, it's too dark to read. -- Groucho Marx
|
|
|
|
|
Congratulations! You have just reinvented COBOL!
|
|
|
|
|
Natural language will never be used for programming, because natural language isn't suitable for strict logic. Otherwise, no one would have had to invent symbolic logic. Symbolic logic is the foundation of computing, it's no accident that Turing was a logician. You can't translate logic into natural language without introducing ambiguity, and it's worse trying to go the other way because you're starting with ambiguity.
|
|
|
|
|
No, not in the near term. American English is way too imprecise to be used as a 'reliable' programing language. Way too many opportunities for misinterpretation.
|
|
|
|
|
So you've traced the evolution from machine language, to assembly, to high level languages. And you also note why the change occurred. Before I could answer your question, I have to ask why would programming move to a natural language to describe the program? Would natural language programming languages offer any benefit over a high level language? All I see is downsides.
|
|
|
|
|
"Just as most programmers today warn people not to use assembler, probably future programmers will warn people not to use anything other than natural language." - Quantum Robin
Please don't go down this rabbit hole. I really don't want to see a resurgence of COBOL...
|
|
|
|
|
For a few reasons I doubt it including that natural language is very imprecise.
Another reason though might be more obscure. I write about how humans can adapt genetically and strategically to the future as our ecology undergoes a radical change from tribal ecology to Civilization. On chapter is about what a person needs to know which includes certain things like Critical Thinking skills so a person can discern truth, science including biology because it describes humans, law because it describes the human environment, etc. I do recommend that a person know a foreign language because it teaches them about their own language. I also recommend that a person learn a programming language. Not necessarily for use on a job, but so they know how machines communicate and think. If we develop machines that can communicate with us in our natural language, we are going to naturally make mistakes communicating with machines and about distinguishing what machines are. We do need to keep that in mind.
|
|
|
|
|
In the long term, the question will be irrelevant - there won't be "programmers" or "languages". Systems will develop themselves. Eventually AI will reach the stage where it can "think" semi-creatively and identify the problem, and from that a solution which it can implement. By semi-creatively I mean, for instance: a hospital administration system that is itself able to identify trends in patient data (e.g. outcomes for groups treated in a certain way are "better" than those treated differently - which involves it being told, or having learnt, what "better" looks like). Having identified such (complex) trends it can then adjust treatment plans accordingly, because systems will be interconnected far more than they already are. It may never reach the stage of being fully "creative", i.e. coming up with entirely novel ideas; however eventually there will be such little demand for human programmers that the requirement to write in a "computer" language rather than natural language would be irrelevant. It's a pretty bleak outlook, not just for developers, but for all mankind since while there will be localisation of solutions, pretty much everything will be an amorphous blob of "the system" which will be taking all the decision making away from us. And of course, scope for hacking would be tremendous - in the situation above, just consider if someone switches the definition of "better" to mean "dead"... 
|
|
|
|
|
Programming languages will end up being increasingly high-level until they become identical to natural language. You will eventually be able to write all your programs in English, Portuguese, or any other natural language, although you will also be able to mix that with instructions of the kind used in today's programming languages whenever you think that's more efficient or clearer.
An intelligent compiler will ask for clarification whenever there's an ambiguity and may suggest improved wordings to resolve the issue. Writing a program will end up being a conversation with an intelligent machine which anyone could handle even if they know nothing about programming - it will be a collaboration with an intelligent system which is in itself an expert programmer. The error messages will be comments and questions just like the ones you'd get if you were co-writing a program with a human programmer. ("When you say "print the result of that part", do you mean this part [a section of the code is highlighted], and do you want it printed to the screen or the printer?")
None of that will stop you putting in a line of C or any other programming language if you want to, but most of the work will simply be done in natural language, typically at a much higher level with the compiler working out how to carry out the tasks asked of it. The end user will also become a programmer, telling the machine how (s)he would prefer things to be done, and the machine will comply. That will rarely be done through anything other than natural language.
AGI = artificial general intelligence
A general intelligence is a more powerful kind of intelligence than a specialised intelligence which can only handle limited tasks. A general intelligence can learn to handle any task. Humans are the only things we currently know of which have general intelligence, and because that's natural intelligence, humans are NGI (natural general intelligence).
NLP = natural language programming
NLP can also be used to mean natural language processing though. This kind of NLP is part of what is needed to support the other kind of NLP because you can't have natural language programming if you can't process natural language.
The AGI system will give you what you most likely want and will then adjust any aspects of it which you aren't happy with. It will not drag you through a menu of all possible options item by item, but will wait instead until you ask for the button to behave in a particular way. The aim is to use artificial general intelligence.
User: Make a button for that.
[Button appears.]
User: A bit bigger, and make it green.
[Button grows bigger and turns green.]
User: Put it here.
[Button moves to the correct location.]
...
(Some time later):-
User: When the cursor's on this button, turn it blue.
[Button turns blue. (AGI system knows that that's more likely what's wanted than turning the cursor blue.)]
User: Make its corners rounded.
[Button changes shape (and retains new shape even when cursor is moved away).]
Etc.
Plain English Programming may be able to become full NLP (natural language programming) if enough people interact with it and extend the range of phrases it can handle, so while it may only handle a subset of English today, that is not an inherent restriction on it. It can keep improving as people write code to support more words. For that reason, it is arguably not a step towards NLP (natural language programming) because it arguably already is NLP (natural language programming). We will only find out when enough code is written to handle all words an all possible uses of them. I think it will run into difficulties with ambiguities, but little additions to the program could fix that. AGI (artificial general intelligence) will study PEP (Plain English Programming) in the future to see what it could have done if the world had got behind it in 2006.
Approach #1: Brute Force Crowd Source. It is the method used in Amazon's ALEXA, Apple's SIRI, Wolfram's ALPHA, Microsoft's CORTANA, Google's HOME, etc. In all these cases, a programmer imagines a question or command that a user will give the machine, and then he writes specific code to answer that specific question ("Alexa, what is the temperature outside?") or carry out that particular command ("Alexa, turn on the living room lights"). Get enough imaginative programmers to write enough routines, et voila! Apparently Intelligent machines that actually exist and work and learn and grow, today.
Approach #2: Dynamically-Generated-User-Tweaked code. This is essentially what I describe here...
If the programmer is happy with the generated code, (s)he can approve of it and it needn't be saved because it will generate correctly each time before compiling - a label would be attached to the high-level NLP (Natural Language Programming) program to tell the compiler that it compiles correctly. If the generated code isn't right though (or isn't complete), that label will not be attached to the NLP (Natural Language Programming) code and the support code will need to be saved as part of the program instead. Some of that support code could still be auto-generated initially, creating the loop and setting up the count, for example, while leaving the programmer to fill in the content of the loop manually.
Approach #2 is an optional intermediate step towards approach #3. Approach #3 is the one where you build AGI (artificial general intelligence) first so that it can solve all the programming problems itself. The idea is that instead of the human writing the difficult bits of code to complete a program, the human teaches the AGI (artificial general intelligence) how to write the difficult bits of code so that it won't need help with the same kind of problem the next time. It's all about giving the AGI (artificial general intelligence) system more and more problem-solving skills until it can do as good a job as the best human programmers.
|
|
|
|
|
Code Project Forums Members,
Again:
Programming languages will end up being increasingly high-level until they become identical to natural language. You will eventually be able to write all your programs in English, Portuguese, or any other natural language, although you will also be able to mix that with instructions of the kind used in today's programming languages whenever you think that's more efficient or clearer.
An intelligent compiler will ask for clarification whenever there's an ambiguity and may suggest improved wordings to resolve the issue. Writing a program will end up being a conversation with an intelligent machine which anyone could handle even if they know nothing about programming - it will be a collaboration with an intelligent system which is in itself an expert programmer. The error messages will be comments and questions just like the ones you'd get if you were co-writing a program with a human programmer. ("When you say "print the result of that part", do you mean this part [a section of the code is highlighted], and do you want it printed to the screen or the printer?")
None of that will stop you putting in a line of C or any other programming language if you want to, but most of the work will simply be done in natural language, typically at a much higher level with the compiler working out how to carry out the tasks asked of it. The end user will also become a programmer, telling the machine how (s)he would prefer things to be done, and the machine will comply. That will rarely be done through anything other than natural language.
AGI = artificial general intelligence
A general intelligence is a more powerful kind of intelligence than a specialised intelligence which can only handle limited tasks. A general intelligence can learn to handle any task. Humans are the only things we currently know of which have general intelligence, and because that's natural intelligence, humans are NGI (natural general intelligence).
NLP = natural language programming
NLP can also be used to mean natural language processing though. This kind of NLP is part of what is needed to support the other kind of NLP because you can't have natural language programming if you can't process natural language.
The AGI system will give you what you most likely want and will then adjust any aspects of it which you aren't happy with. It will not drag you through a menu of all possible options item by item, but will wait instead until you ask for the button to behave in a particular way. The aim is to use artificial general intelligence.
User: Make a button for that.
[Button appears.]
User: A bit bigger, and make it green.
[Button grows bigger and turns green.]
User: Put it here.
[Button moves to the correct location.]
...
(Some time later):-
User: When the cursor's on this button, turn it blue.
[Button turns blue. (AGI system knows that that's more likely what's wanted than turning the cursor blue.)]
User: Make its corners rounded.
[Button changes shape (and retains new shape even when cursor is moved away).]
Etc.
Plain English Programming may be able to become full NLP (natural language programming) if enough people interact with it and extend the range of phrases it can handle, so while it may only handle a subset of English today, that is not an inherent restriction on it. It can keep improving as people write code to support more words. For that reason, it is arguably not a step towards NLP (natural language programming) because it arguably already is NLP (natural language programming). We will only find out when enough code is written to handle all words an all possible uses of them. I think it will run into difficulties with ambiguities, but little additions to the program could fix that. AGI (artificial general intelligence) will study PEP (Plain English Programming) in the future to see what it could have done if the world had got behind it in 2006.
Approach #1: Brute Force Crowd Source. It is the method used in Amazon's ALEXA, Apple's SIRI, Wolfram's ALPHA, Microsoft's CORTANA, Google's HOME, etc. In all these cases, a programmer imagines a question or command that a user will give the machine, and then he writes specific code to answer that specific question ("Alexa, what is the temperature outside?") or carry out that particular command ("Alexa, turn on the living room lights"). Get enough imaginative programmers to write enough routines, et voila! Apparently Intelligent machines that actually exist and work and learn and grow, today.
Approach #2: Dynamically-Generated-User-Tweaked code. This is essentially what I describe here...
If the programmer is happy with the generated code, (s)he can approve of it and it needn't be saved because it will generate correctly each time before compiling - a label would be attached to the high-level NLP (Natural Language Programming) program to tell the compiler that it compiles correctly. If the generated code isn't right though (or isn't complete), that label will not be attached to the NLP (Natural Language Programming) code and the support code will need to be saved as part of the program instead. Some of that support code could still be auto-generated initially, creating the loop and setting up the count, for example, while leaving the programmer to fill in the content of the loop manually.
Approach #2 is an optional intermediate step towards approach #3. Approach #3 is the one where you build AGI (artificial general intelligence) first so that it can solve all the programming problems itself. The idea is that instead of the human writing the difficult bits of code to complete a program, the human teaches the AGI (artificial general intelligence) how to write the difficult bits of code so that it won't need help with the same kind of problem the next time. It's all about giving the AGI (artificial general intelligence) system more and more problem-solving skills until it can do as good a job as the best human programmers.
Code Project Forums Members,
Do you agree with the affirmations that I quoted above?
If not, why you don't agree with the affirmations that I quoted above?
|
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
