Actions

Difference between revisions of "Algoliterary Encounters"

From Algolit

 
(2 intermediate revisions by the same user not shown)
Line 6: Line 6:
 
==Algoliterary works==
 
==Algoliterary works==
 
A selection of works by members of Algolit presented in other contexts before.
 
A selection of works by members of Algolit presented in other contexts before.
* [[Oulipo recipes]]
 
 
* [[i-could-have-written-that]]
 
* [[i-could-have-written-that]]
 
* [[The Weekly Address, A model for a politician]]
 
* [[The Weekly Address, A model for a politician]]
 
* [[In the company of CluebotNG]]
 
* [[In the company of CluebotNG]]
 +
* [[Oulipo recipes]]
  
 
==Algoliterary explorations==
 
==Algoliterary explorations==
Line 22: Line 22:
 
==== Datasets ====
 
==== Datasets ====
 
Working with Neural Networks includes collecting big amounts of textual data.
 
Working with Neural Networks includes collecting big amounts of textual data.
A comparison with the collection of words of the Library of St-Gilles:
+
We compared a 'regular' size with the collection of words of the Library of St-Gilles.
 
* [[Many many words]]  
 
* [[Many many words]]  
  
Line 56: Line 56:
  
 
=== How a Machine Might Speak ===
 
=== How a Machine Might Speak ===
If a neural network could speak, what would it say?
+
If a computer model for language comprehension could speak, what would it say?
 
* [[We Are A Sentiment Thermometer]]
 
* [[We Are A Sentiment Thermometer]]
  

Latest revision as of 13:50, 2 November 2017

About

Algoliterary works

A selection of works by members of Algolit presented in other contexts before.

Algoliterary explorations

This chapter presents part of the research of Algolit over the past year.

What the Machine Writes: a closer look at the output

Two neural networks are presented more closely, what content do they produce?

How the Machine Reads: Dissecting Neural Networks

Datasets

Working with Neural Networks includes collecting big amounts of textual data. We compared a 'regular' size with the collection of words of the Library of St-Gilles.

Public datasets

Most commonly used public datasets are gathered at Amazon. We looked closely at the following two:

Algoliterary datasets

Working with literary texts allows for poetic beauty in the reading/writing of the algorithms. This is a small collection used for experiments.

From words to numbers

As machine learning is based on statistics and math, in order to process text, words need to be transformed to numbers. In the following section we present three technologies to do so.

Different vizualisations of word embeddings
Inspecting the technique behind word embeddings

How a Machine Might Speak

If a computer model for language comprehension could speak, what would it say?

Sources

The scripts we used and a selection of texts that kept us company.