Actions

Difference between revisions of "Algoliterary Encounters"

From Algolit

 
(40 intermediate revisions by 4 users not shown)
Line 1: Line 1:
 
__NOTOC__
 
__NOTOC__
 
+
== About ==
Start of the Algoliterary Encounters catalog.
+
* [[An Algoliterary Journey]]
 
 
== Introduction ==
 
 
 
* [[Algolit's Algoliterary Journey|Algolit]]
 
 
* [[Program]]
 
* [[Program]]
  
 
==Algoliterary works==
 
==Algoliterary works==
* [[Oulipo recipes]]
+
A selection of works by members of Algolit presented in other contexts before.
 
* [[i-could-have-written-that]]
 
* [[i-could-have-written-that]]
* Obama, 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==
 +
This chapter presents part of the research of Algolit over the past year.
 +
 
=== What the Machine Writes: a closer look at the output ===
 
=== What the Machine Writes: a closer look at the output ===
 +
Two neural networks are presented more closely, what content do they produce?
 
* [[CHARNN text generator]]
 
* [[CHARNN text generator]]
 
* [[You shall know a word by the company it keeps]]
 
* [[You shall know a word by the company it keeps]]
  
 
=== How the Machine Reads: Dissecting Neural Networks ===
 
=== How the Machine Reads: Dissecting Neural Networks ===
 
 
==== Datasets ====
 
==== Datasets ====
* [[Many many words]] - introduction to the datasets with calculation exercise
+
Working with Neural Networks includes collecting big amounts of textual data.
* [[The data (e)speaks]] - espeak installation
+
We compared a 'regular' size with the collection of words of the Library of St-Gilles.
 +
* [[Many many words]]  
  
=====Common public datasets=====
+
=====Public datasets=====
 +
Most commonly used public datasets are gathered at [https://aws.amazon.com/public-datasets/ Amazon].
 +
We looked closely at the following two:
 
* [[Common Crawl]]  
 
* [[Common Crawl]]  
 
* [[WikiHarass]]
 
* [[WikiHarass]]
  
 
=====Algoliterary datasets=====
 
=====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.
 +
* [[The data (e)speaks]]
 
* [[Frankenstein]]
 
* [[Frankenstein]]
* [[Learning from Deep Learning]]  
+
* [[Learning from Deep Learning]]
* [[AnarchFem]]  
+
* [[nearbySaussure]]
* [[Tristes Tropiques]]
+
* [[astroBlackness]]
  
 
==== From words to numbers ====
 
==== 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.
 
* [[A Bag of Words]]
 
* [[A Bag of Words]]
 
* [[A One Hot Vector]]
 
* [[A One Hot Vector]]
 +
* [[About Word embeddings|Exploring Multidimensional Landscapes: Word Embeddings]]
 +
* [[Crowd Embeddings|Word Embeddings Casestudy: Crowd embeddings]]
  
==== Special Focus: Word Embeddings ====
+
===== Different vizualisations of word embeddings =====
* [[About Word embeddings]]
 
* [[Crowd Embeddings]]
 
 
 
===== Different portraits of word embeddings =====
 
 
* [[Word embedding Projector]]
 
* [[Word embedding Projector]]
* [[5 dimensions 32 graphs]]
 
 
* [[The GloVe Reader]]
 
* [[The GloVe Reader]]
  
===== Inspecting the technique =====
+
===== Inspecting the technique behind word embeddings =====
* [[word2vec_basic.py]] - in piles of paper
+
* [[word2vec_basic.py]]
* [[softmax annotated]]
 
 
* [[Reverse Algebra]]
 
* [[Reverse Algebra]]
  
 
=== How a Machine Might Speak ===
 
=== How a Machine Might Speak ===
 +
If a computer model for language comprehension could speak, what would it say?
 
* [[We Are A Sentiment Thermometer]]
 
* [[We Are A Sentiment Thermometer]]
  
 
== Sources ==
 
== Sources ==
===Code===
+
The scripts we used and a selection of texts that kept us company.
*[https://gitlab.constantvzw.org/algolit/algolit/tree/master/algoliterary_encounter Algoliterary Gitlab]
+
* [[Algoliterary Toolkit]]
*[https://gitlab.constantvzw.org/algolit/algolit/tree/master/algoliterary_encounter/algoliterary-toolkit/cgi-example jinja-cgi interface template]
+
* [[Algoliterary Bibliography]]
*[https://gitlab.constantvzw.org/algolit/algolit/blob/master/algoliterary_encounter/algoliterary-toolkit/text-punctuation-clean-up.py text-punctuation-clean-up.py]
 
 
 
===Bibliography===
 
* [[Algoliterary Bibliography]] - Reading Room texts
 
  
  
 
[[Category:Algoliterary-Encounters]]
 
[[Category:Algoliterary-Encounters]]

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.