GLUE: A Multi-Task Benchmark for NLU

Authors: Wang et al. Year: 2018 ArXiv/Link: https://arxiv.org/abs/1804.07461

Summary

Foundational benchmark suite for natural language understanding tasks enabling standardized evaluation.

Key Concepts

• NLU benchmark
• Multi-task evaluation
• Standardized metrics
• Task diversity
• Transfer learning evaluation

Impact

Became standard benchmark for NLP progress

Category

Benchmark Papers

---