Tu et al - Multi-hop Reading Comprehension across Multiple Documents

Tags: papers, nlp

• Tu, Ming, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He, and Bowen Zhou. “Multi-Hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs.” In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2704–13. Florence, Italy: Association for Computational Linguistics, 2019. https://doi.org/10.18653/v1/P19-1260.
• video: https://vimeo.com/384732193

• proposes a heterogenous document entity graph with different granularities, uses a graph neural network

• notes that there are two types of reading comphrension problems:

  1. adding a layer to neural rc models using doc and entity level info

  2. graph neural networks