Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models
This work provides a low-cost solution for human authors struggling with writer's block, offering a tool to assist in generating text.
This paper addresses the problem of writer's block by fine-tuning a natural language generation model. The fine-tuning incorporates right context, optional entities, size, genre, and a paragraph summary as conditioning, achieving excellent results with a low cost of USD 150.
It is standard procedure these days to solve Information Extraction task by fine-tuning large pre-trained language models. This is not the case for generation task, which relies on a variety of techniques for controlled language generation. In this paper, we describe a system that fine-tunes a natural language generation model for the problem of solving Writer's Block. The fine-tuning changes the conditioning to also include the right context in addition to the left context, as well as an optional list of entities, the size, the genre and a summary of the paragraph that the human author wishes to generate. Our proposed fine-tuning obtains excellent results, even with a small number of epochs and a total cost of USD 150. The system can be accessed as a web-service, and all the code is released. A video showcasing the interface and the model is also available.