learn.ifs.name

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Wang et al., 2019, GLUE (7th International Conference on Learning Representations (ICLR 2019))

Subscriber deck — free during early access

1 cards in “3 Tasks” · whole deck

3 Tasks

  1. Which nine tasks make up GLUE?
    Grouped by type, with their metrics:
    typetasks (metric)
    single sentenceCoLA acceptability (Matthews corr.), SST-2 sentiment (acc.)
    similarity, paraphraseMRPC (acc./F1), QQP (acc./F1), STS-B similarity score (Pearson/Spearman)
    inferenceMNLI (matched/mismatched acc.), QNLI, RTE, WNLI (acc.)
    • Wang et al., 2019, GLUE (7th International Conference on Learning Representations (ICLR 2019)), §3

Source

  • Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy and Samuel R. Bowman. 2019. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In 7th International Conference on Learning Representations (ICLR 2019). https://openreview.net/forum?id=rJ4km2R5t7