Natural Language Processing Tutorial

1Introduction to Natural Language ...
2Natural Language Processing Basics
3Named entity recognition
4Sentiment Analysis
5Topic modelling

1. Introduction to Natural Language Processing

1 Exabyte (10^18) of data is created on the internet daily, amounting to roughly the equivalent of data in 250 million DVDs. And most of this data is in the form of text. what do we do with these mountains of data? So in the Age of Content, “Context” is becoming more important. For example, the computer read some number ‘30”. What should it mean? Is it the number of days in a month or 30 rupees or weight of some bag in kilograms? Or the waist size of jeans? So the context is becoming more and more important.

Unstructured data (also known as free-form text) comprises 70%-80% of the data available on computer networks. The information content of this resource is unavailable to governments, businesses, and individuals unless humans read these texts. Natural language processing can be applied to characterize, interpret, or understand the information content of the free-form text.

Natural language processing technology is designed to derive meaningful and actionable data from freely written text. But the natural language processing involves a lot more than a computer recognizing a list of words.

Below are some of the use cases where NLP can be used in the real world.

    • Chatbots: Virtual personal assistants also are known as chatbots are rapidly making their presence in the digital world. Businesses are using chatbots across support, marketing, healthcare verticals.
    • Speech Recognition: This is where devices like Alexa, Siri, Google home and any other virtual assistants come to picture. NLP has developed its roots in healthcare with speech recognition, allowing clinicians to transcribe notes for efficient EHR data entry for nearly two decades.
    • Credit worthiness assessment: Nowadays many banks and lending companies leveraging NLP and assess the credit worthiness of clients with little or no credit history. For example, students who got a job first time and start earning money have no or little credit history. But they are potential customers to banks for giving loans. Even if these clients have never used credit before, most of them still use smartphones, browse the internet and engage in other activities that leave a lot of digital footprints. NLP algorithms analyze geolocation data, social media activity, browsing behaviour to derive insights into their habits, peer networks, and strength of their relationships. By analyzing thousands of client-related variables, the software generates a credit score highly predictive of customer’s further activity.
    • Neural Machine Translation: What has previously seemed like an awkward attempt to imitate the professional translation has now substantially improved, but neural machine translation (NMT)has taken the improvements even further. Google, Amazon, and Microsoft are competing to deliver the best machine translation today.
    These are just a few examples of NLP application. There are many more NLP applications like news aggregation, sentiment analysis, hiring and recruitment applications.
2019 Edugrad. All Rights Reserved.