Automatic Novel Generation

Notes:

Automatic novel generation is a subfield of natural language processing (NLP) that involves using computer algorithms to generate complete, coherent, and grammatically correct novels or story-like texts. This can be done either by training a model on a large dataset of existing novels or by using some form of generative techniques.

The process of automatic novel generation typically involves several steps:

  1. Data collection: A large dataset of existing novels is collected to train the model.
  2. Text preprocessing: The collected text is preprocessed to remove any unwanted characters or symbols.
  3. Model training: A machine learning model, such as a recurrent neural network (RNN) or a transformer, is trained on the preprocessed text dataset.
  4. Generation: Once the model is trained, it can be used to generate new, original novels by sampling from the learned probability distribution of the training dataset.
  5. Evaluation: Generated novels are evaluated by humans for coherence, grammar, and readability.

Automatic novel generation is still an active area of research, and the quality of the generated novels is still a subject of debate. However, recent advancements in deep learning, natural language processing, and generative models have led to the generation of novels that are increasingly coherent, grammatically correct and sometimes even indistinguishable from human-written novels.

The main applications for automatic novel generation are to help authors overcome writer’s block, or to provide a tool for creative writing and storytelling. It can also be used in the entertainment industry such as video games or movies to generate a story, or to create a new story for an existing game.

Resources:

References:

See also:

100 Best Botnik Videos | 100 Best Predictive Keyboard Videos | Automated Journalism Meta Guide | Automatic Book Generation | Computational Creativity & Dialog Systems | Generative Literature & Natural Language Processing | Generative Text & Natural Language Processing

[Apr 2019]