papers AI Learner
The Github is limit! Click to go to the new site.

Cognitive Graph for Multi-Hop Reading Comprehension at Scale

2019-05-14
Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, Jie Tang

Abstract

We propose a new CogQA framework for multi-hop question answering in web-scale documents. Inspired by the dual process theory in cognitive science, the framework gradually builds a \textit{cognitive graph} in an iterative process by coordinating an implicit extraction module (System 1) and an explicit reasoning module (System 2). While giving accurate answers, our framework further provides explainable reasoning paths. Specifically, our implementation based on BERT and graph neural network efficiently handles millions of documents for multi-hop reasoning questions in the HotpotQA fullwiki dataset, achieving a winning joint $F_1$ score of 34.9 on the leaderboard, compared to 23.6 of the best competitor.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.05460

PDF

https://arxiv.org/pdf/1905.05460


Comments

Content