Natural Language Processing | Part 1
To strengthen the connection between your conscious and subconscious is to gain access to a map and compass, as you travel through parallel worlds.
-Kevin Michel
Nowadays, we talk to Siri, Alexa, Cortana, etc. They can understand the slang we use regular nowadays, and they are also not confined to a digital dictionary now. They know the context we are using in words. They are as smart as human while talking. How is it possible? Once, there was a time when they only understood the code, which will compile and run if it’s 100% free of spelling and syntactic errors.
Natural languages or Human languages contains:
- Large, diverse vocabularies.
- Words with several different meanings.
- Speakers with different accents.
- All other sorts of exciting wordplay.
If this were the only scenario, then Siri and all others would have existed since the 90s, but we (Humans) also make a linguistic faux pas when writing and speaking, like slurring words together, leaving out key details. Most of us rely more on being descriptivists rather than being a prescriptivist. So, making a system with a rules only approach won’t solve our problem. The challenge faced by a computer or a machine to understand and speak our language led to Natural Language Processing, or NLP, an interdisciplinary field combining Computer Science and Linguistics.
Natural Language Processing
Natural Language Processing is a branch of Artificial Intelligence that deals with the interaction between computers and human using the natural language. The ultimate objective of NLP is to read, decipher, understand, and helpfully make sense of Human Language.
It is a discipline that focuses on the interaction between data science and human language and is scaling to lots of industries. Today NLP is flourishing thanks to the vast improvements in access to data and the increase in computational power, allowing practitioners to achieve meaningful results in areas like healthcare, media, finance, and human resources.
Why do we need NLP?
Knowing about a word type is beneficial, but many words have multiple meanings (Polysemy). A digital dictionary alone isn’t enough to resolve this ambiguity, so computers also need to know some Grammar. A machine needs to understand what a Human is trying to convey, and we can’t be deal everything with according to grammar rules and dictionary vocab. We need a machine or a system that can understand Human Language when communicating with others without using Linguistic standards.
In a concise form, machines should have the ability to learn a language with context.
NLP mainly explores two big ideas:
- Natural Language Understanding (How we get meaning out of Combinations?)
- Natural Language Generation (How to generate language from Translations?)
Applications of NLP
A few of the applications of NLP are:
- Language Translation.
- Text Summarization.
- Dialog Systems / Chatbots.
- Sentiment Analysis.
- Speech Recognition.
- Autocorrect.
- Question-Answering System.
- Book Generation.
- Document AI.
If you liked reading it, Part 1 of the NLP series I’m coming up with would come up within the upcoming days. Tune in to learn more.
