GLUEベンチマーク
https://gluebenchmark.com/
#GLUE
https://paperswithcode.com/dataset/glue
https://huggingface.co/datasets/glue
load_metric
にGLUEを指定した例
https://huggingface.co/docs/datasets/loading.html#distributed-setup
過去の例
https://github.com/nyu-mll/jiant
(~2021/10)
(deprecated)
https://github.com/nyu-mll/GLUE-baselines
含むデータとタスク(
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
5.3より引用)
natural language inference (MNLI, QNLI, RTE)
sentence similarity (MRPC, QQP and STS-B)
sentence similarity 気になる
grammaticality (CoLA)
sentiment analysis (SST-2)
データは8つ含む(らしい)