https://github.com/torvaney/human-language-model

Test a human, character-level language model on a given corpus
https://github.com/torvaney/human-language-model

elm language-model

Last synced: 28 days ago
JSON representation

Test a human, character-level language model on a given corpus

• Host: GitHub
• URL: https://github.com/torvaney/human-language-model
• Owner: Torvaney
• Created: 2019-02-16T12:13:21.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2019-02-18T16:31:25.000Z (almost 6 years ago)
• Last Synced: 2024-11-12T12:45:50.562Z (3 months ago)
• Topics: elm, language-model
• Language: Elm
• Homepage: https://torvaney.github.io/projects/human-language-model.html
• Size: 41 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Human Language Model

Test your language model!

[![](screenshot.png)](https://torvaney.github.io/projects/human-language-model.html)

[Try it out](https://torvaney.github.io/projects/human-language-model.html)

## What is it?

Test the accuracy of your "language model" on a given corpus (sort of).

### What is a "language model"?

> A statistical language model is a probability distribution over sequences of words. Given such a sequence, say of length m, it assigns a probability to the whole sequence.

(from [Wikipedia](https://en.wikipedia.org/wiki/Language_model))

## How does it work

The programme takes a plain text file, and splits it into non-overlapping chunks.

You then have to guess which character came next, after the chunk shown. Chunks are

show in random order.

## How to build

The app is written in Elm, and can be compiled to Html (and javascript) like so:

1. `elm make src/elm/Main.elm`

1. `open index.html`