In previous task T342614, we have experimented with different models for simplification.
Focusing on English datasets for fine-tuning and evaluation, we found that some of the models (e.g. Flan-T5) showed generally good performance.
Here, we want to address the question whether the same model could be applied with similar good results in other languages beyond English.
Description
Description
Status | Subtype | Assigned | Task | ||
---|---|---|---|---|---|
Open | MGerlach | T342614 Models for text summarization using LLMs | |||
Open | MGerlach | T361947 Evaluate simplification in multilingual setting |
Event Timeline
Comment Actions
weekly update:
- started setting up the experiments for evaluating fine-tuned Flan-T5 on other languages
- will run experiments next week