Lecture

Natural Language Generation

Related lectures (28)

Natural Language Generation: Decoding Techniques and Training Challenges

Covers decoding methods and training challenges in natural language generation.

Natural Language Generation: Decoding & Training

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

Explores air pollution analysis using wind data, probability distributions, and trajectory models for air quality assessment.

Text Generation: Basics and Evaluation

Covers the basics of text generation and the challenges of evaluating generated text using content overlap metrics, model-based metrics, and human evaluations.

Probability Theory: Midterm Solutions

Covers the solutions to the midterm exam of a Probability Theory course, including calculations of probabilities and expectations.

Normal Distribution: Characteristics and Examples

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

Gaussian Mixture Models: Data Classification

Explores denoising signals with Gaussian mixture models and EM algorithm, EMG signal analysis, and image segmentation using Markovian models.

Multivariate Statistics: Normal Distribution

Introduces multivariate statistics, covering normal distribution properties and characteristic functions.

Natural Language Generation: Task

On NLG covers basics, autoregressive models, decoding methods, and challenges in text generation.

Deep Learning for NLP

Introduces deep learning concepts for NLP, covering word embeddings, RNNs, and Transformers, emphasizing self-attention and multi-headed attention.

Advanced Probabilities: Random Variables & Expected Values

Explores advanced probabilities, random variables, and expected values, with practical examples and quizzes to reinforce learning.

Determinantal Point Processes and Extrapolation

Covers determinantal point processes, sine-process, and their extrapolation in different spaces.

Concentration Inequalities

Covers concentration inequalities and sampling methods for estimating unknown distributions, with a focus on population infection rates.

Diffusion Models

Explores diffusion models, focusing on generating samples from a distribution and the importance of denoising in the process.

Natural Language Generation

Explores Natural Language Generation, covering neural models, biases, ethics, and evaluation challenges.

Markov Chain Monte Carlo: Sampling and Convergence

Explores Markov Chain Monte Carlo for sampling high-dimensional distributions and optimizing functions using the Metropolis-Hastings algorithm.

Normal Distribution: Characteristics and Z-scores

Explores normal distribution characteristics, Z-scores, probability in inferential statistics, sample effects, and binomial distribution approximation.

Powder Characterisation: Physical, Chemical, Morphology

Explores the physical, chemical, and morphological analysis of powders, emphasizing sampling accuracy and quality control.

Review Session: Module 1

Introduces inferential statistics, covering sampling, central tendency, dispersion, histograms, z-scores, and the normal distribution.

Operators: Data Transfer and Manipulation

Covers the concept of operators for data transfer and manipulation between activities, including aggregation, distribution, and social operators.