CFGNN: Cross Flow Graph Neural Networks for Question Answering on Complex Tables

Authors

  • Xuanyu Zhang Beijing Normal University

DOI:

https://doi.org/10.1609/aaai.v34i05.6506

Abstract

Question answering on complex tables is a challenging task for machines. In the Spider, a large-scale complex table dataset, relationships between tables and columns can be easily modeled as graph. But most of graph neural networks (GNNs) ignore the relationship of sibling nodes and use summation as aggregation function to model the relationship of parent-child nodes. It may cause nodes with less degrees, like column nodes in schema graph, to obtain little information. And the context information is important for natural language. To leverage more context information flow comprehensively, we propose novel cross flow graph neural networks in this paper. The information flows of parent-child and sibling nodes cross with history states between different layers. Besides, we use hierarchical encoding layer to obtain contextualized representation in tables. Experiments on the Spider show that our approach achieves substantial performance improvement comparing with previous GNN models and their variants.

Downloads

Published

2020-04-03

How to Cite

Zhang, X. (2020). CFGNN: Cross Flow Graph Neural Networks for Question Answering on Complex Tables. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 9596-9603. https://doi.org/10.1609/aaai.v34i05.6506

Issue

Section

AAAI Technical Track: Natural Language Processing