← Back to resources

Supervised Learning

A machine learning method in which models are trained using labelled data.

What Is Supervised Learning

Supervised learning is a machine learning approach where models are trained on labelled examples. Each training input is paired with a known output, allowing the model to learn patterns that map inputs to expected results.

How Supervised Learning Works

During training, the model predicts outputs for labelled inputs and compares predictions with ground truth labels. An optimisation process updates model parameters to reduce prediction error over many iterations.

  • prepare labelled datasets
  • train a model with a defined objective function
  • validate performance on unseen samples
  • deploy and monitor model behaviour in production

Types of Supervised Learning (classification and regression)

Supervised learning is commonly split into classification and regression tasks. Classification predicts discrete categories, while regression predicts continuous numeric values.

  • classification: spam detection, intent labels, language identification
  • regression: score prediction, quality estimation, demand forecasting

Role in Machine Translation and NLP

In NLP and translation, supervised learning powers tasks such as sequence tagging, quality estimation, and bilingual mapping. Labelled corpora allow systems to learn grammar, terminology usage, and context sensitive predictions that improve translation workflows.

Examples of Supervised Learning Models

Typical supervised models include:

  • logistic regression and support vector machines
  • decision trees and random forests
  • neural networks, including transformer based architectures
  • sequence models for tagging and translation quality tasks

Related Terms

Semantic Similarity

A measure used in natural language processing to determine how similar two texts are in meaning.

Speech Recognition

Technology that converts spoken language into written text using machine learning models.

Style Guide

A document defining linguistic, stylistic, and formatting rules for translation.

Related Resources

Machine Learning

A field of AI where systems learn patterns from data to make predictions or generate content.

Reinforcement Learning

A machine learning method in which an agent learns decision-making through rewards and penalties.

Gradient Descent

An optimisation algorithm that iteratively updates model parameters to reduce prediction error.

Backpropagation

A learning process used in neural networks to adjust internal weights after comparing predictions with expected results.

Fine-Tuning

The adaptation of a pre-trained model for a specific task through additional training on focused data.

Federated Learning

A machine learning approach where models are trained across distributed devices or servers without centralising raw data.

Explore Trad AI

Open the workspace