my net house

WAHEGURU….!

Natural Language processing

NLP which mostly stands for Natural Language Processing and most of  the time it is also considered as teaching things to computer so it can understand, speak, read and write words, As we all speak, read and write so computer do the same in terms of Machine learning algorithms 😉

NLP is s field of computer science and computational linguistics which is
driven by Advance Machine learning as well as uses Artificial intelligence
for making decisions for particular set of problems.

Most of the problems are solved or being solved Using NLP, As Artificial intelligence
is developed as same as Human Neural Network understands the things, here we can also talk about test developed by Alan Turing about prediction of words those are responded by machine, Turing proposed a human Elevator would judge the conversation happened between human and machine and conversation will only happen in the text medium that is using Keyboard only. If the evaluator cannot reliably tell the machine from the human (Turing originally suggested that the machine would convince a human 70% of the time after five minutes of conversation), the machine is said to have passed the test. The test does not check the ability to give correct answers to questions, only how closely answers resemble those a human would give.

Now for example we can take input from machine:

As ____Man___ is related to ___woman____

King is related to _______ ?

the particular answer will be ___queen___ (That is exact machine predicted)

So What’s under the hood? (How machine learns by itself?(we should call it himself or herself :P))

To understand that at first we need to understand How we learn? In our mind all the words are represented as image or set of images in the 3D space, whatever we think or imagine comes in the form of vector representation  for example If I think about King my mind will show me an image if King and all things those are related to king like queen, army or kingdom

So that is basically A machine is doing but we feed data in terms of vector form
Now meaning(king)-meaning(man)+meaning(woman) = ?

 

So when we remove the meaning of man from meaning of King we get something like
royal, so royal woman could be princess or Queen, But as we know in general sense Queen is more close to king rather than army,
prince or princess So what machine actually Understood? Machine took vector representation of Royal(y-axis) and Non-royal(x-axis) and in that graph queen and King are closest so Machine returned Queen

Vector(King)-Vector(man)+Vector(woman) = Vector(queen)

Now we can conclude Machine can Speak, read, write, Now from Engineering point of View we can replicate our knowledge in terms of decision making to tell the patient about any particular disease his/her heart has or can get in near future, such system can also be used to predict the health of our Heart. In 2010, the cost of cardiovascular disease in the U.S. was about $444 billion.

Using NLP we can cut down the cost of Diagnosis and  cure/prevention treatment, Which could be considered as string step towards the using AI in Medical field. Playing sake one can also test out this https://github.com/rkomartin/heart-disease-example project
To understand the real meaning of NLP ans AI combined in easy one can go to
http://www.cleverbot.com/ and ask it various questions, For example I asked it :

 

Me: Do you know about Programming languages
and reply was; Yes, I know about Python!

 

 

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: