Automatic Generation of German Drama Texts Using Fine Tuned GPT-2 Models
This addresses the problem of generating drama texts in German for researchers or creators, but it is incremental as it builds on existing GPT-2 methods with specific fine-tuning steps.
The study tackled automatic generation of German drama texts by fine-tuning GPT-2 models to generate scene outlines and scenes from keywords, using datasets like GerDraCor and DTA. The models performed well in automatic evaluations but showed poor quality in manual analysis, possibly due to dataset or training issues.
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.