Korean Language Understanding Evaluation (KLUE) benchmark is a series of datasets to evaluate natural language understanding capability of Korean language models. KLUE consists of 8 diverse and representative tasks, which are accessible to anyone without any restrictions. With ethical considerations in mind, we deliberately design annotation guidelines to obtain unambiguous annotations for all datasets. Furthermore, we build an evaluation system and carefully choose evaluations metrics for every task, thus establishing fair comparison across Korean language models.
19 PAPERS • 1 BENCHMARK
MuMiN is a misinformation graph dataset containing rich social media data (tweets, replies, users, images, articles, hashtags), spanning 21 million tweets belonging to 26 thousand Twitter threads, each of which have been semantically linked to 13 thousand fact-checked claims across dozens of topics, events and domains, in 41 different languages, spanning more than a decade.
4 PAPERS • 3 BENCHMARKS
Wikipedia Title is a dataset for learning character-level compositionality from the character visual characteristics. It consists of a collection of Wikipedia titles in Chinese, Japanese or Korean labelled with the category to which the article belongs.
3 PAPERS • NO BENCHMARKS YET
This is a movie review dataset in the Korean language. Reviews were scraped from Naver Movies.
0 PAPER • 1 BENCHMARK