Skip to content

A Neural Probabilistic Language Model - built on German name dataset for learning

Notifications You must be signed in to change notification settings

lukaskuhn-lku/Bengio2003-Names

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Probabilistic Name Generator in Torch

This project is based on the paper "A Neural Probabilistic Language Model" (Bengio et al., 2003) and the very informative videos by Andrej Karpathy on building probabilistic language models in Pytorch.

I am using a german namedataset to train a probabilistic language model with 10-dimensional embeddings, a hidden layer with 100 neurons (configurable) and a cross-entropy loss function.

In inference you can generate new names based on the probabilities outputted by the neural net.

Sample names are:

  • marlo
  • emmergo
  • walrainmart
  • tilldalfine
  • thande
  • walde
  • berga
  • bilthaherd
  • herolin
  • gerwi

The training, evaluation and test have all been written as a learning exercise and are not the most efficient way of building a neural net.

About

A Neural Probabilistic Language Model - built on German name dataset for learning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published