Candidate Sampling
Candidate sampling is a family of training-time optimization techniques used in machine learning to reduce the computational cost of models that must choose among a very large number of output classes.
Natural Language Processing
Explore Natural Language Processing through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Neural Networks
Articles that also belong to these categories. Counts cover all of Natural Language Processing.
All articles (239)Machine Learning (92)Large Language Models (58)AI Benchmarks (42)Deep Learning (37)Information Retrieval (29)AI Models (24)Artificial Intelligence (24)Open Source AI (23)Data & Datasets (15)AI Companies (9)Model Evaluation (9)Transformer Models (9)Meta AI (8)Speech & Audio AI (8)OpenAI (7)Training & Optimization (7)AI Ethics (6)AI Safety (6)AI Tools & Products (6)Computer Vision (6)Generative AI (6)People (6)AI Agents (5)Prompt Engineering (5)Developer Tools (4)Neural Networks (4)AI Code Generation (3)Algorithms (3)Anthropic (3)Mathematics (3)Reasoning Models (3)Statistics (3)AI Alignment (2)AI History (2)AI Research (2)Chinese AI (2)Diffusion Models (2)Google DeepMind (2)Healthcare AI (2)Model Architecture (2)Multimodal AI (2)AI Inference (1)Computer Science (1)Education AI (1)Enterprise AI (1)Legal AI (1)Microsoft (1)Mixture of Experts (1)NVIDIA (1)Research Organizations (1)Voice AI (1)
Showing 1-4 of 4 articles
Cross-encoder
A cross-encoder is a neural network architecture that scores a pair of texts by feeding them jointly into a single transformer (such as BERT) and reading out one scalar score for the pair, for example a…
Embedding Layer
An embedding layer is a neural network component that acts as a trainable lookup table, mapping discrete integer indices (such as word IDs, user IDs, or category codes) to dense, continuous-valued vectors.
Full Softmax
Full softmax (also called the standard softmax or exact softmax) is the softmax computation that calculates a probability for every possible output class in a classification model