Natural Language Generation: Task

Related lectures (30)

Page 1 of 3

Covers decoding methods and training challenges in natural language generation.

Explores challenges in natural language generation, decoding algorithms, training issues, and reward functions.

Explores sampling a probability distribution and structure functions in statistical analysis.

Covers the implementation of Markov Chain Monte Carlo (MCMC) with the Metropolis algorithm for sampling from posterior distributions.

Explores max entropy, Shannon's entropy, Lagrange multipliers, and Monte Carlo sampling techniques.

Discusses language models, focusing on fixed-context neural models and recurrent neural networks.

Covers the characteristics and importance of the normal distribution, including examples and treatment scenarios.

Covers generative models with a focus on self-attention and transformers, discussing sampling methods and empirical means.

Covers the theory of sampling, focusing on statistics for mathematicians.

Introduces the Boltzmann Machine, covering expectation consistency, data clustering, and probability distribution functions.