Machine Learning (ML) is a type of Artificial Intelligence (AI) that allows software applications to carry out actions that they’ve not been explicitly programmed to do. ML algorithms use existing data to predict new outputs allowing it to ‘learn’ patterns to predict outcomes.
Imagine you want to teach a computer to understand human language, specifically the sentiment of a sentence, whether it is positive, neutral, or negative. Providing the computer with examples of this data, such as “I had a fantastic holiday” telling the algorithm that this is positive or “I had a terrible time at the concert” and teaching the algorithm this is negative, builds the foundations it needs to begin recognising patterns in the words and phrases used.
The more samples the programme reads, the better it becomes at identifying the sentiment of new, unseen sentences.
This is a very simple example of what ML models can do for Natural Language Processing (NLP). By using similar scenarios, ML can teach computers to understand written sentences and spoken words, so that the programmes can go on to translate languages, summarise text, and so on.