Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Neural Nets for NLP 2021 - Conditioned Generation

Graham Neubig via YouTube

Overview

Limited-Time Offer: Up to 75% Off Coursera Plus!
7000+ certificate courses from Google, Microsoft, IBM, and many more.
This course on Neural Networks for Natural Language Processing (NLP) covers topics such as Encoder-Decoder Models, Conditional Generation, Ensembling, Evaluation, and Types of Data to Condition On. The course teaches skills in calculating the probability of a sentence, different search algorithms for generation, ensembling techniques, and various evaluation methods. The teaching method includes lectures and practical examples. This course is intended for students or professionals interested in neural networks, NLP, and language modeling.

Syllabus

Intro
Language Models • Language models are generative models of text
Conditioned Language Models
Calculating the Probability of a Sentence
Conditional Language Models
One Type of Language Model Mikolov et al. 2011
How to Pass Hidden State?
The Generation Problem
Ancestral Sampling
Greedy Search
Beam Search
Ensembling . Combine predictions from multiple models
Linear Interpolation • Take a weighted average of the M model probabilities
Log-linear Interpolation • Weighted combination of log probabilities, normalize
Linear or Log Linear?
Parameter Averaging
Ensemble Distillation (e.g. Kim et al. 2016)
Stacking
Still a Difficult Problem!
From Speaker/Document Traits (Hoang et al. 2016)
From Lists of Traits (Kiddon et al. 2016)
From Word Embeddings (Noraset et al. 2017)
Basic Evaluation Paradigm
Human Evaluation Shared Tasks
Embedding-based Metrics
Perplexity
Which One to Use?

Taught by

Graham Neubig

Reviews

Start your review of Neural Nets for NLP 2021 - Conditioned Generation

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.