KEMT/zpwiki
32
1
Fork 9
Code Issues Pull Requests Releases Wiki Activity

Update pages/interns/yussef_ressaissi/README.md

Browse Source
This commit is contained in:
dano 2025-06-30 12:00:51 +00:00
parent 020dc8ca83
commit 77aba37f85
1 changed files with 13 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
pages/interns/yussef_ressaissi/README.md
View File

@ -15,13 +15,18 @@ Goal: Evaluate and improve language models for summarization in Slovak medical o
Tasks: Tasks:
- Get familiar with basic tools and prepare working environment: HF transformers, datasets, lm-evaluation-harness, HF trl 1. Get familiar with basic tools
- Read several recent papers about summarization using LLM and write a report. - and prepare working environment: HF transformers, datasets, lm-evaluation-harness, HF trl
- Get familiar how to perform and evaluate document summarization using language models in Slovak. - Read several recent papers about summarization using LLM and write a report.
- Pick summarization datasets and models. Evaluate several models for evaluation using ROUGE and BLEU metrics. - Get familiar how to perform and evaluate document summarization using language models in Slovak.
- Describe the experiments. Summarize results in a table. Describe the results. 2. Make a comparison experiment
- 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. - Pick summarization datasets and models. Evaluate several models for evaluation using ROUGE and BLEU metrics.
- Run new expriments and write down the results. - Describe the experiments. Summarize results in a table. Describe the results.
- Publish the fine-tuned models in HF HUB. Publish the paper from the project. 3. 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.
4. Report and disseminate
- Prepare a final report with analysis, experiments and conclusions.
- Publish the fine-tuned models in HF HUB. Publish the paper from the project.