Natural Language Processing
Natural Language Processing is a subfield of natural language, computer science, and artificial intelligence concerned with the interactions between computers and human language, in particular how to program computers to process and analyze large amounts of natural language data.
So if I visually express this it will be something like NLP is a baby product of all the three fields.
Let’s see why NLP is considered as subfield of all the three major fields?
Computer Science -> Programming
Artificial Intelligence -> You will apply Machine Learning Models
Human Language -> Text or Voice.
Does this explain NLP? I guess no! One question which pops up in my mind is that what is the purpose of the NLP?
The purpose of the Natural Language Processing is to read, decipher into machine language, understand and make sense of the human languages. Basically it is the way to teach the machine to understand what is given in spoken or written word.
Remember few years back we have to type everything into Google search to get effective results. Now we just use Google Voice Assistant or Siri ( if you are Apple user ). What changed?
Well it’s not so hard to guess! Google developed apps like Google Translate and Voice Assistant where we dictate something to our Android device that captures our voices in audio files, convert it into text, process the text’s data and search it over internet or convert them back to audio and present it to user.
Frequently used techniques in NLP
- Sentiment Analysis
- Topic Modelling
- Text Generation
- Named Entity Recognition
- Text Summarization
Sentiment Analysis is the process of analyzing the text to determine whether the given text is positive, negative or neutral.
Example: Take a simple example of a twitter post.
Does the text used to deliver information about COVID Vaccine kit delivery is a positive, negative or neutral sentiment?
This type of problem can be dealt in Sentiment Analysis where we will try to find what is the reaction of the people towards certain texts or information!!
Topic Modelling is a statistical framework which helps us to understand large document collections, not just to find individual documents but to understand the general themes present in the collection.
Text generation is the task of generating text which are similar to the human written texts.
Named Entity Recognition
Named Entity Recognition is a technique used in NLP for extracting the entities from the texts.
Example: Ram is an employee in Google. He is currently in Hyderabad. He is residing there from November 2019.
So the Named Entity Recognition will identifies entities like Name, Location, Date, Organization etc.
Organization : Google
Date: November 2019
Text Summarization is used for summarizing the large texts into smaller one.
Example: A news article can be summarized into one line news.
Here we can see that the article has been summarized into text as “Coronavirus | India’s COVID cases drop to lowest in over 100 days”
Applications of Natural Language Processing
- Reviewing the text into good one or bad one.
- Categories of article.
- Prediction of genre of books.
- Machine translator.
- Classification of language and many more…..