Skip to content

Dataset · indonlp

Indonesian natural language understanding benchmark

indonlp/indonlu

Set of tasks for training and evaluating NLP models in Indonesian.

What's inside

The IndoNLU benchmark combines text resources for training, evaluating, and analyzing natural language understanding (NLU) systems in Indonesian (Bahasa Indonesia). Includes text classification, token classification, and question-answering tasks. Total dataset size ranges from 10 to 100 thousand examples.

What you can do with it

  • Evaluating multilingual and Indonesian LLMs on NLU tasks
  • Fine-tuning models for text classification and entity extraction in Indonesian
Tasks
Question answering, Text classification, Token classification
Languages
Indonesian
Size
10K–100K rows
Downloads this month
1.9K
Likes
45

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("indonlp/indonlu")