ReCoRD:缩小人类与机器常识阅读理解之间的差距
计算与语言
2018-10-31 v1
摘要
我们提出了一个大规模数据集ReCoRD,用于需要常识推理的机器阅读理解。在该数据集上的实验表明,最先进的MRC系统的表现远远落后于人类表现。ReCoRD代表了未来研究缩小人类与机器常识阅读理解差距的挑战。ReCoRD可在 http://nlp.jhu.edu/record 获取。
引用
@article{arxiv.1810.12885,
title = {ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension},
author = {Sheng Zhang and Xiaodong Liu and Jingjing Liu and Jianfeng Gao and Kevin Duh and Benjamin Van Durme},
journal= {arXiv preprint arXiv:1810.12885},
year = {2018}
}
备注
14 pages