Natural Language Processing

We are living in an advanced world nowadays. Everyone is so engulfed with technology, that we cannot think of us living without technology and its applications for a moment. And we are creating an enormous amount of data with every passing second. And this data includes a lot of things, messages exchanged between 2 entities, on any platform like whatsapp, messenger or simple text messages, call histories, internet browsed.

No extracting something important from that data and making it useful according to our needs sometimes becomes quite time consuming, and a lot of efforts are needed of an individual for this process. The process of extracting information from textual form of data is known as Natural Language Processing.

We can use this extracted information in different algorithms and for different computations.

And by using NLP and its components, we can organize the unorganized data and can perform many automated tasks. Now we will talk about different functions and techniques of it.

  1. POS Tagging - A simple way to mark words in sentences as nouns, adjectives, adverbs, e.t.c
  2. Stemming - It is the process of reducing inflected (or sometimes derived) words to their word stem, base or root form—generally a written word form. The stem need not be identical to the root of the word; it is usually sufficient that related words map to the same stem, even if this stem is not in itself a valid root. Algorithms for stemming have been studied in computer science since the 1960s. Many search engines treat words with the same stem as synonyms as a kind of query expansion, a process called conflation.
  3. Lemmatization -  It usually refers to doing things properly with the use of a vocabulary and morphological analysis of words, normally aiming to remove inflectional endings only and to return the base or dictionary form of a word, which is known as the lemma . If confronted with the token saw, stemming might return just s, whereas lemmatization would attempt to return either see or saw depending on whether the use of the token was as a verb or a noun. The two may also differ in that stemming most commonly collapses derivationally related words, whereas lemmatization commonly only collapses the different inflectional forms of a lemma. Linguistic processing for stemming or lemmatization is often done by an additional plug-in component to the indexing process, and a number of such components exist, both commercial and open-source.
  4. Word Embedding : Word embedding is the collective name for a set of language modeling and feature learning techniques in NLP where words or phrases from the vocabulary are mapped to vectors of real numbers. Conceptually it involves a mathematical embedding from a space with many dimensions per word to a continuous vector space with a much lower dimension.
  5. Sentiment Analysis : A form of subjective analysis that uses Natural Language Processing techniques to identify different sentiments. These sentiments can be of different consumers to take out some information about their point of view, judging of mood via voice analysis or written text analysis.
  6. Semantic Text Similarity : Process of identifying similarities between two or more texts with respect to the meaning of text rather than analyzing the syntax of any text. And here we are talking about similarities, not relationship, both things are quite different.
  7. Text Summarization : It is a process of shortening up of a text by identifying important points of data and creating a summary using these points. The main goal of text summarization is to retain the maximum amount of useful information by maximum shortening of a text, without changing the meaning of the original text.

Workflow of NLP Project :

  1. Preprocessing : It means cleaning up of dirty, unorganized data and making it into structured and organized form of data. NLP can be considered as a set of tools which can be used for structuring natural language for different purposes. And here our dataset is being referred to as “corpus”, since it is composed of textual information. Pre-processing of data using NLP, it is known as Text Normalization or preparation of data.
  2. Structuring : In this process, we identify the elements that are needed. We have discussed some of the techniques needed for structuring the data already.
  3. Analysis : Extraction of features for carrying out different tasks.
  4. Transformation : Process of transforming the collected information into some interpretable source in order to take some decisions, observe it, analyze it.

0 likes followers Views

HelpFeaturesMade with in INDPrivacyAbout
© 2020