Microsoft KEAR surpasses human performance on CommonsenseQA benchmark — “When given a question that requires drawing on prior knowledge and five answer choices, our latest model— KEAR, Knowledgeable External Attention for commonsense Reasoning—performs better than people answering the same question, calculated as the majority vote among five individuals.”
Links for 2021-12-23
Links for 2021-12-23
Links for 2021-12-23
Microsoft KEAR surpasses human performance on CommonsenseQA benchmark — “When given a question that requires drawing on prior knowledge and five answer choices, our latest model— KEAR, Knowledgeable External Attention for commonsense Reasoning—performs better than people answering the same question, calculated as the majority vote among five individuals.”