Notebooks from the Seminar:
Georg Trogemann, Christian Heck, Mattis Kuhn, Ting Chun Liu
Basic Seminar Material/Sculpture/Code
Compact seminar 11 - 4 pm | 31.01.2022 until 11.02.2022
Online @ BigBlueButton
Academy of Media Arts Cologne
Email: [email protected], [email protected], [email protected]
The generation of text by means of deep neural nets (NLG) has spread rapidly. Among other things, text-based dialog systems such as chatbots, assistance systems (Alexa/Siri) or robot journalism are increasingly used in news portals, e-commerce and social media; wherever context-based, natural language or reader-friendly texts are to be generated from structured data. Deep writing techniques have also found their way into the arts and literature with the help of models such as ELMo (Embeddings from Language Models), BERT (Bidirectional Encoder Representations from Transformers) or GPT-2/3 (Generative Pre-Training Transformer).
The goal of the seminar is that at the end each student has produced (a) text based on one of the neural language models mentioned above. No matter if poem, prose, novella, essay, manifesto, shopping list or social bot.
The course is intended as a general introduction to programming. It will not only teach skills to generate texts, but also the basics of Python, a universal programming language that can be used to program images, PDFs or web applications. Furthermore, Python is the most widely used language in programming Artificial Intelligences, especially Deep Neural Nets.
We ask for registration at [email protected] until 20.09.2021. No prior knowledge of programming is required to participate in the basic seminar.
Python: Booleans, If - Else, While-loop
Python: Strings, Files, Try & Except
Python: Tuples, Dictionaries, Set
dataset-list < some resources of datasets & archives
scrape-load_textcorpora < some basic examples and code-snippets to srape, load and walk through datasets
scraper_wikipedia < extract text of specific wikipedia articles
0-order text generation < random word generation, wiederholung von Char, String and List
Data cleaning and Parsing < python method for parsing text as data
1-order text generation and Probability < probability calculation
Markov Chain - Background and knowledge < basic knowledge of Markov chain
Markov Chain - Basic (Second Order Text Generation < Basic usage of Markov chain with second order text generation.
Markov Chain - N-order Text Generation < N-Order text generation.
Markov Chain - OOP < Markov Chain based on object oriented programming.
Markov Chain - Markovify-library < Markov Chain based on github repo https://github.com/jsvine/markovify
Additional - Markov Chain with Image Image Generation based on Markov Chain
ANN-in-Keras.ipynb < Dense Neural Network with Keras
+ working with Copilot
Text generation with LSTM < Text generation with RNN/LSTM
HuggingFace Pipeline < the HuggingFace way to use state-of-the-art NLP-models for inference
aitextgen < Python tool for text-based AI training and generation using GPT-2
Executing the Notebooks:
- You can run, execute and work on the Notebooks in typing following button:
