ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension

TL;DR

ReCoRD is a large-scale dataset designed to evaluate and advance machine reading comprehension that requires commonsense reasoning, highlighting the significant gap between current AI systems and human understanding.

Contribution

The paper introduces ReCoRD, a new dataset for commonsense reading comprehension, providing a benchmark to measure and improve AI's reasoning capabilities.

Findings

State-of-the-art models perform far below human levels

ReCoRD challenges future research to improve AI commonsense reasoning

Dataset is publicly available for benchmarking

Abstract

We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning. Experiments on this dataset demonstrate that the performance of state-of-the-art MRC systems fall far behind human performance. ReCoRD represents a challenge for future research to bridge the gap between human and machine commonsense reading comprehension. ReCoRD is available at http://nlp.jhu.edu/record.