# Automatic Generation of German Drama Texts Using Fine Tuned GPT-2 Models

arXiv: https://arxiv.org/abs/2301.03119 · HTML: https://mlsanity.com/paper/2301.03119/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 8 Jan 2023.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Strategies for Structuring Story Generation](https://mlsanity.com/paper/1902.01109/) (2019)
- [Do Massively Pretrained Language Models Make Better Storytellers?](https://mlsanity.com/paper/1909.10705/) (2019)
- [Automatic Story Generation: Challenges and Attempts](https://mlsanity.com/paper/2102.12634/) (2021)
- [THEaiTRE: Artificial Intelligence to Write a Theatre Play](https://mlsanity.com/paper/2006.14668/) (2020)
- [Consistency and Coherency Enhanced Story Generation](https://mlsanity.com/paper/2010.08822/) (2020)
- [THEaiTRE 1.0: Interactive generation of theatre play scripts](https://mlsanity.com/paper/2102.08892/) (2021)

## Built on by (most cited first, 2 of 2)

- [Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions](https://mlsanity.com/paper/2305.10435/) (2023)
- [BrAIcht, a theatrical agent that speaks like Bertolt Brecht's characters](https://mlsanity.com/paper/2504.20552/) (2025)

## Abstract (arXiv)

This study is devoted to the automatic generation of German drama texts. We suggest an approach consisting of two key steps: fine-tuning a GPT-2 model (the outline model) to generate outlines of scenes based on keywords and fine-tuning a second model (the generation model) to generate scenes from the scene outline. The input for the neural model comprises two datasets: the German Drama Corpus (GerDraCor) and German Text Archive (Deutsches Textarchiv or DTA). In order to estimate the effectiveness of the proposed method, our models are compared with baseline GPT-2 models. Our models perform well according to automatic quantitative evaluation, but, conversely, manual qualitative analysis reveals a poor quality of generated texts. This may be due to the quality of the dataset or training inputs.