forked from KEMT/zpwiki
.. | ||
README.md |
title | published | taxonomy | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
Youssef Ressaissi | true |
|
IAESTE Intern Summer 2025, 1.7. - 31.8.2025
Goal: Evaluate and improve language models for summarization in Slovak medical or legal domain.
Tasks:
- Get familiar with basic tools and prepare working environment: HF transformers, datasets, lm-evaluation-harness, HF trl
- Read several recent papers about summarization using LLM and write a report.
- Get familiar how to perform and evaluate document summarization using language models in Slovak.
- Pick summarization datasets and models. Evaluate several models for evaluation using ROUGE and BLEU metrics.
- Describe the experiments. Summarize results in a table. Describe the results.
- Improve performance of a languge model. Use more data. Prepare a domain-oriented dataset and finetune a model. Maybe generate artificial data to imporve summarization.
- Run new expriments and write down the results.
- Publish the fine-tuned models in HF HUB. Publish the paper from the project.