Techniques & Methods
Text Classification
Text classification assigns labels to text inputs from a fixed set of categories. Applications include spam detection, sentiment analysis, intent classification, topic tagging, and content moderation. It is one of the most widely deployed NLP tasks in production.
Modern text classification uses fine-tuned transformer models that achieve near-human accuracy on many benchmarks. Zero-shot classification with LLMs has further democratized the capability, removing the need for task-specific labeled data.
Authority Links
Related Terms
Applications
Sentiment Analysis
Automatically identifying and categorizing expressed opinions in text to determine attitude.
Techniques & Methods
Named Entity Recognition (NER)
Identifying and classifying named entities in text into predefined categories like people and places.
Core Concepts
Supervised Learning
Models trained on labeled data, learning to predict outcomes from inputs.
Techniques & Methods
Fine-Tuning
Continuing the training of a pre-trained foundation model on a smaller, curated dataset to specialize its behavior, style, or domain expertise without losing its general capabilities.