Establishing a Human Baseline for the Winograd Schema Challenge

By David Bender. 2015

41 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Douwe Kiela
2. Samuel R. Bowman
3. Mohit Bansal
4. Adina Williams
5. Yi Tay
6. Tristan Thrush
7. Yonatan Belinkov
8. Nikita Nangia

Citations in the corpus

• Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark (2019, background): “Bender (2015) also estimates human performance on the original public Winograd Schema Challenge (WSC) data.”
• Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality (2022, background): “Wino-grad schema examples are easily handled by humans, and commonsense reasoning is said to be required [4].”
• A Knowledge Hunting Framework for Common Sense Reasoning (2018, background): “WSC problems are simple for people to solve (human participants in one study performed at 92% accuracy (Bender, 2015)) but difficult for automatic systems.”