Is multi-hop reasoning really explainable? Towards benchmarking reasoning interpretability

• Main Authors: LV, Xin, CAO, Yixin, HOU, Lei, LI, Juanzi, LIU, Zhiyuan, ZHANG, Yichi, DAI, Zelin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/7317; https://ink.library.smu.edu.sg/context/sis_research/article/8320/viewcontent/2021.emnlp_main.700.pdf
• Institution: Singapore Management University

Multi-hop reasoning has been widely studied in recent years to obtain more interpretable link prediction. However, we find in experiments that many paths given by these models are actually unreasonable, while little work has been done on interpretability evaluation for them. In this paper, we propos...