Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark
This provides a conservative benchmark for evaluating AI progress in language understanding, showing that current models are close to human performance in data-poor settings.
The study measured human performance on the GLUE benchmark using non-expert crowdsourced annotators, who achieved an average score of 87.1 and outperformed the state of the art on six out of nine tasks, indicating limited headroom for further progress.
The GLUE benchmark (Wang et al., 2019b) is a suite of language understanding tasks which has seen dramatic progress in the past year, with average performance moving from 70.0 at launch to 83.9, state of the art at the time of writing (May 24, 2019). Here, we measure human performance on the benchmark, in order to learn whether significant headroom remains for further progress. We provide a conservative estimate of human performance on the benchmark through crowdsourcing: Our annotators are non-experts who must learn each task from a brief set of instructions and 20 examples. In spite of limited training, these annotators robustly outperform the state of the art on six of the nine GLUE tasks and achieve an average score of 87.1. Given the fast pace of progress however, the headroom we observe is quite limited. To reproduce the data-poor setting that our annotators must learn in, we also train the BERT model (Devlin et al., 2019) in limited-data regimes, and conclude that low-resource sentence classification remains a challenge for modern neural network approaches to text understanding.