Tokenization
Tokenization splits text or other input into units that an AI model converts into identifiers and processes.
Explore AIstify's latest reporting, research, and expert analysis tagged with "natural language processing", collected in one continuously updated archive.
Tokenization splits text or other input into units that an AI model converts into identifiers and processes.
A transformer is a neural network architecture built on attention and used in modern language, vision, audio, video, and multimodal AI models.
An attention mechanism helps an AI model focus on the most relevant parts of its input when interpreting information or generating an output.
Semantic search uses embeddings to retrieve information by meaning and context, finding relevant results even when documents use different words.
Perplexity measures how uncertain a language model is when predicting a sequence, with lower values indicating better prediction.
A recurrent neural network (RNN) is a deep learning model that carries information across sequential inputs such as text, speech, and time-series data.
NLU enables computer systems to identify meaning, intent, entities, and relationships in human language.
NLG is the branch of AI that produces human-readable language from data, prompts, representations, or structured plans.
Prompt engineering is the practice of designing instructions, context, examples, and output rules that help generative AI perform tasks reliably.
Masked language modeling trains a model to reconstruct hidden tokens using the surrounding context on both sides.
XLM-R is a multilingual transformer encoder that supports cross-lingual classification, entity recognition, and language understanding tasks.
Named entity recognition (NER) is an NLP task that finds and classifies people, places, organizations, dates, products, and other entities in text.
An embedding is a numerical representation that places related words, images, documents, or other items close together in a mathematical space.
Multimodal AI is artificial intelligence that understands or generates multiple data types, including text, images, audio, video, and sensor input.
Word error rate (WER) measures speech-recognition accuracy from word substitutions, deletions, and insertions compared with a reference transcript.