A field of AI focused on enabling computers to understand, interpret, and generate human language.
Natural language processing (NLP) covers tasks such as translating between languages, summarizing documents, answering questions, detecting sentiment in reviews, extracting names and dates from text, recognizing speech, and powering chatbots.
Early NLP relied on hand-written grammar rules and statistical methods that counted word patterns. Deep learning, and especially the transformer architecture introduced in 2017, transformed the field, leading to large language models that handle many tasks with a single system. Challenges remain, including ambiguity, sarcasm, cultural context, and support for languages with less available training data, such as many regional languages of South Asia. Everyday NLP shows up in email autocomplete, voice assistants, search engines, and spam filters.
A software program that holds a conversation with people through text or voice, answering questions or helping complete simple tasks.
EmbeddingA list of numbers (a vector) that represents a word, sentence, image, or other item so that similar items have similar vectors.
Large Language ModelAn AI model trained on vast amounts of text to understand and generate human-like language, code, and other content.
Sentiment AnalysisUsing natural language processing to determine whether a piece of text expresses a positive, negative, or neutral opinion.
Speech RecognitionTechnology that converts spoken language into written text, allowing computers to understand voice commands and transcribe audio.
TransformerA neural network architecture, introduced in 2017, that uses attention mechanisms and underpins most modern large language models.
What structured, unstructured and semi-structured data are, with real business examples, a side-by-side comparison table and how AI is turning unused documents and recordings into usable data.
Natural language processing explained through tools you already use, from spam filters and autocorrect to voice assistants and chatbots, plus practical business uses.
How intelligent document processing reads invoices, forms and contracts, how it differs from OCR and RPA, and where human review still belongs.