💡 Natural Language Processing (NLP)

Natural Language Processing (NLP)#

The field of processing and understanding human language with machines.

Important

✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.

What it is#

Natural language processing teaches machines to understand and generate human language — text and speech. It bridges unstructured language and computation, from parsing meaning to producing fluent output.

Its tasks#

NLP spans classification (sentiment, topic), named-entity recognition, translation, summarization, question answering, and generation. Its architectures moved from RNNs and LSTMs to the transformer, behind BERT and GPT-style models.

Its turning point#

NLP was the first great success of self-supervised pretraining — models learn from masked-token prediction on huge unlabeled text, then fine-tune on a smaller labeled task. That pretrain-then-finetune recipe reset the field and now underlies search, chatbots, and translation.

Theme: AI & ML Concepts · All terminology

Hint

Mind map — connected ideas

Computer Vision (CV) · Neural Networks · Embedding · Full Annotation · LSTM — Long Short-Term Memory Networks · Weak Supervision

Hint

More in AI & ML Concepts

AI (Artificial Intelligence) · Classification Models · Computer Vision (CV) · Decision Trees · Linear Models · LLMs (Large Language Models) · Logistic Regression · Machine Learning (ML) · Medical AI · Neural Networks · Regression Models · Support Vector Machines (SVMs) · Target Variable