2 AI linguistics
You might come across some interesting AI acronyms such as Large Language Models (LLMs) or Natural Language Generation (NLG). These acronyms are a part of a branch of AI called Natural Language Processing (NLP).
These technologies enable computers to understand, generate, and respond to human language in new ways. From suggesting words while typing a message, to giving ideas for a creative project, AI provides further support for our creative endeavors.
This video explains the meaning behind the acronyms and how this branch of AI is changing how humans interact with AI.
Download this video clip.Video player: Video 3
Transcript: Video 3
Voiceover:
Have you ever wondered how your mobile phone understands what you are saying?
Or how can it suggest words while you are typing a message?
That is all thanks to some clever technology behind some interesting acronyms.
Natural Language Processing, or NLP, is a large branch of AI that empowers computers to understand and react to human language.
It is like sorting through a huge library of books — categorising them, summarising their content, and knowing exactly where to find the information you need.
NLP involves several tasks such as translation, sentiment analysis, speech recognition and topic segmentation.
A Latin and Asian alphabet character, a woman talking on a phone, a mood chart and a piece of green paper full of scribbles appear around the acronym NLP.
A subfield of NLP is Natural Language Generation, or NLG. This specialised branch of AI gives computers the ability to craft text that is not only understandable but also contextually relevant.
It is the driving force behind the creation of various text content. Imagine a journalist who writes articles on many topics.
They collect information, organise their thoughts, and then write a story. NLG operates in a similar fashion, but it is a system that processes data and weaves it into a narrative, be it a financial summary, a weather forecast, or a product description.
Advancing further, we encounter Large Language Models, or LLMs, which represent a more sophisticated use of AI in language.
Trained in text collections, LLMs can perform complex tasks requiring contextual understanding, such as holding conversations or providing answers to inquiries.
For instance, imagine a well-travelled individual who can recount tales and converse in various languages.
An LLM also has an extensive array of texts and can discuss a multitude of topics, giving the impression of conversing with a seasoned traveller.
While NLG focuses on generating new text from structured data, LLMs are designed to produce text that is meaningful and contextually fitting.
This distinction highlights the impressive abilities of large language models, which go beyond the typical functions of natural language generation.
Now you might be wondering how these technologies are applied in the real world today. Microsoft Copilot for instance, harnesses both NLG and LLM technologies to offer users a range of assistance, from summarising information to providing coding support.
Similarly, GitHub Copilot is an AI-powered tool that enhances developers’ productivity by suggesting relevant code snippets for the task at hand.
However, it is crucial to remember that these are tools designed to assist us. And as with any tool, they must be used responsibly.
Video 3
Interactive feature not available in single page view (see it in standard view).
- Natural Language Processing (NLP) is a branch of AI that helps computers understand and respond to human language. Recently, Large Language Models (LLMs) improved NLP applications.
- LLMs are advanced AI models trained in large amounts of text data. They predict words in sequences, enabling them to perform tasks like text generation, summarization, translation, and classification.
- LLMs are a key part of generative AI, which focuses on creating new content. By using LLMs, generative AI can produce human-like text, making it a useful tool in content creation.