Natural Language Processing: A Discussion for NLP Working and Applications

  • Avinash Mishra
  • Sep 28, 2019
  • NLP
  • Last Updated: Sep 28, 2019
Natural Language Processing: A Discussion for NLP Working and Applications title banner

NLP or Natural Language Processing is basically an approach to find out information out of a text to make it understandable to a machine as same as humans do, as we know, the whole idea of machine learning is to provide human brain-like capabilities to a machine, so as our human brain is capable of understanding text and speech, we tend to provide the same ability to our machine so that it can automatically understand a text or speech in its natural form.

 

We read so many texts through emails, web pages, apps, etc. imagine if a machine could itself understand this information, how much automation can be done in the field of text manipulation and sentiment analysis? Natural language processing is a hot topic now but has been studied for the past 5 decades, one of its applications that is used a lot nowadays is google Alexa, ever imagined how it recognizes your voice and follows your instruction? All power of Natural Language Processing. Machines nowadays are being more and more capable of understanding and manipulating text and speech.

 

Topics Covered

 

  1. Introduction
  2. Working of Natural Language Processing
  3. Applications of NLP
  4. Conclusion

 

Working of Natural Language Processing

 

First of all, extracting meaning out of a text is truly a very tough job, When we know that we are making something very tough to possible in machine learning, we use pipelining that means we make small steps in order to complete a whole project by joining these steps. There are many steps in NLP pipelining, taking the idea that we have to find out meaning out of texts, we will do step by step illustration

 

1. Sentence Tokenizing

 

For a given document to analyze, we know that not every sentence in a paragraph relates with each other totally or in general, every sentence has an individual meaning, so consider a text :

 

“Calcutta now Kolkata was the capital of India during the British Raj, until December 1911. Calcutta had become the center of the nationalist movements since the late nineteenth century, which led to the Partition of Bengal by then Viceroy of British India, Lord Curzon. This created massive political and religious upsurge including political assassinations of British officials in Calcutta.”

 

Now see what this paragraph would look after sentence tokenization:

 

“Calcutta now Kolkata was the capital of India during the British Raj, until December 1911”

“ Calcutta had become the center of the nationalist movements since the late nineteenth century, which led to the Partition of Bengal by then Viceroy of British India, Lord Curzon.

This created massive political and religious upsurge including political assassinations of British officials in Calcutta.”

 

Every sentence in the above paragraph is been tokenized.

 

2.  Word Tokenizing

 

As we tokenized sentences in our first step of pipelining, we tokenize each word in the next step of pipelining, let's take an above-tokenized sentence and do word tokenization.

 

“Calcutta now Kolkata was the capital of India during the British Raj, until December 1911”

 

After, word tokenization it will look somewhat like:

 

“Calcutta”, “now”, “ Kolkata”, “ was”, “ the”, “ capital”,  “of”, “ India”, “ during”, “ the”, “British”,“ Raj”, “ until”, “ December”, “ 1911”

 

Whenever there is a space in between words, we do splitting that's how simple it is.

 

3.  Stemming And Lemmatization

 

Stemming refers to cutting down the prefixes or suffixes of words to extract some meaning out, but this technique does not ensure that the word will have some meaning, for example studying, here it will cut ‘ing’ and the remaining word will be ‘study’ which is correct, but in the case of ‘studied’, it will cut ‘ed and the remaining word would be ‘studi’, which is of course incorrect. On the other hand, lemmatization is a process where the lemmatized word will definitely have some meaning. “Bag of words" is a tool used for stemming and lemmatization of words.

 

Other techniques used in pipelining are the identification of stopwords, which can be easily done with the help of python library NLTK. Named Entity Recognition(NER) technique, where we tag out the entities which can be famous people, places, products etc to sort more meaning and part of speech recognition for identification of speech.

Above are some techniques that help the machine to understand the syntax and semantics of the natural language.

 

Applications of NLP

 

1.  Sentiment Analysis: Analyzing text and giving them remarks i.e positive or negative remark in order to analyze the context of a text is known as sentiment analysis. For example, if we have to analyze the reviews given by the public to a movie through comments, then a given set of sentences or words will be given remarks such as positive or negative and then the counts of all positive and negative will give the average ratings of the movie.

 

Sentiment Analysis is one of the prominent application of natural language processing.

 

2.  Chatbots: To help customers with real-time questions and answers, nowadays almost every web product or application is using chatbot as one of the topmost preference, it is a very economical method to provide personalized assistant experience to the user. Bot conversation in many organizations recorded as rating according to feelings of the users to get an idea of the behavioral pattern of the market. We encounter many chatbots on a daily basis which are using NLP to handle users. Companies like Zomato, Uber, Banks chatbots are integrated with their customer service channels, handling off conversations, back and forth, while people can take on more complex and bigger conversations. There are many great examples of NLP based chatbots like X.ai, Xiaoice, Mitsuku, etc.

 

3.  Machine Translation: It is a process from machine translate one natural language to another natural language, for example, you must have seen google translator which translates English to Hindi or any other language which shows how useful this technique is. Machine translation is sometimes not efficient enough because translate language to another language, finding the perfect counterparts and preserving the meaning of the phrase requires advanced statistical and NLP techniques. Machine translation is one of the oldest subfields of artificial intelligence research.

 

4.  Speech Recognition: speech recognition can be seen in many fields, whether it be home automation such as google Alexa or amazon echo and Siri in apple is also an example of speech recognition. Also, Grammarly that is used for the correction of grammatical errors in the document is an example of a natural language processing application.

 

Till now we have seen NLP in power but its working has never been as simple as it is shown, in fact, it is a very complex technique to understand under deep learning, as there are so many syntaxes and semantics in natural language that it is difficult for a  human to master and we here are trying to make this complex thing possible through machine. Over the past when NLP got powered by machine learning algorithms to produce some very optimum results.

 

Natural Language Processing is a technique that is going through advancement every single day and the day it will come to its full potential, it will create miracles in the automation sector.

 

Conclusion

 

Natural language processing in deep learning is a very demanding and promising field of the 21st century, we see towards more advancement as we know it has not grown to its full potential, but with further association with new machine learning algorithms, we can see some more of its application in daily life.

0%

Avinash Mishra

Avinash claims words should be filled in the void of Knowledge and thus, he started writing on various topics that covers, all what is under Sun. His interests range from political pessimism to Technological scepticism.

Trending blogs

  • Introduction to Time Series Analysis: Time-Series Forecasting Machine learning Methods & Models

    READ MORE
  • How is Artificial Intelligence (AI) Making TikTok Tick?

    READ MORE
  • 7 Types of Activation Functions in Neural Network

    READ MORE
  • 7 types of regression techniques you should know in Machine Learning

    READ MORE
  • 6 Major Branches of Artificial Intelligence (AI)

    READ MORE
  • Introduction to Logistic Regression - Sigmoid Function, Code Explanation

    READ MORE
  • What is K-means Clustering in Machine Learning?

    READ MORE
  • Top 10 Big Data Technologies in 2020

    READ MORE
  • Introduction to Linear Discriminant Analysis in Supervised Learning

    READ MORE
  • Convolutional Neural Network (CNN): Graphical Visualization with Code Explanation

    READ MORE
Write a BLOG