Transfer learning and in-context learning for stage direction classification in French
This poster expands our work on stage direction classification in French via fine-tuning pre-trained language models and prompting large language models (LLM), testing new models, hyperparameters and prompts. A new qualitative analysis of LLM results showed limits in our reference annotations, and how LLMs can help identify them.
Institutions
- Universidade de Santiago de Compostela (ES)
- Université de Strasbourg (FR)
- Université de Montréal (CA)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2025-04-19
- DOI
- https://doi.org/10.5281/zenodo.15249772
- Primary Topic
- Speech Recognition and Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 0.00