BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering

04/10/2019
by   Yu Cao, et al.
0

Multi-hop reasoning question answering requires deep comprehension of relationships between various documents and queries. We propose a Bi-directional Attention Entity Graph Convolutional Network (BAG), leveraging relationships between nodes in an entity graph and attention information between a query and the entity graph, to solve this task. Graph convolutional networks are used to obtain a relation-aware representation of nodes for entity graphs built from documents with multi-level features. Bidirectional attention is then applied on graphs and queries to generate a query-aware nodes representation, which will be used for the final prediction. Experimental evaluation shows BAG achieves state-of-the-art accuracy performance on the QAngaroo WIKIHOP dataset.

READ FULL TEXT
research
08/29/2018

Question Answering by Reasoning Across Documents with Graph Convolutional Networks

Most research in reading comprehension has focused on answering question...
research
11/05/2016

Bidirectional Attention Flow for Machine Comprehension

Machine comprehension (MC), answering a query about a given context para...
research
04/24/2017

Ruminating Reader: Reasoning with Gated Multi-Hop Attention

To answer the question in machine comprehension (MC) task, the models ne...
research
10/18/2019

Relational Graph Representation Learning for Open-Domain Question Answering

We introduce a relational graph neural network with bi-directional atten...
research
01/15/2021

Coarse-grained decomposition and fine-grained interaction for multi-hop question answering

Recent advances regarding question answering and reading comprehension h...
research
06/03/2022

QAGCN: A Graph Convolutional Network-based Multi-Relation Question Answering System

Answering multi-relation questions over knowledge graphs is a challengin...
research
04/09/2020

HopGAT: Hop-aware Supervision Graph Attention Networks for Sparsely Labeled Graphs

Due to the cost of labeling nodes, classifying a node in a sparsely labe...

Please sign up or login with your details

Forgot password? Click here to reset