Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks

09/06/2018
by   Linfeng Song, et al.
0

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local coreference information, encoding coreference chains with DAG-styled GRU layers within a gated-attention reader. However, coreference is limited in providing information for rich inference. We introduce a new method for better connecting global evidence, which forms more complex graphs compared to DAGs. To perform evidence integration on our graphs, we investigate two recent graph neural networks, namely graph convolutional network (GCN) and graph recurrent network (GRN). Experiments on two standard datasets show that richer global information leads to better answers. Our method performs better than all published results on these datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/11/2020

Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network

Multi-hop reading comprehension across multiple documents attracts much ...
research
06/07/2019

Multi-hop Reading Comprehension through Question Decomposition and Rescoring

Multi-hop Reading Comprehension (RC) requires reasoning and aggregation ...
research
11/07/2022

Complex Reading Comprehension Through Question Decomposition

Multi-hop reading comprehension requires not only the ability to reason ...
research
06/12/2019

Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

Multi-hop reading comprehension requires the model to explore and connec...
research
10/16/2019

Why can't memory networks read effectively?

Memory networks have been a popular choice among neural architectures fo...
research
12/02/2022

Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning

The opaqueness of the multi-hop fact verification model imposes imperati...
research
04/04/2020

Graph Sequential Network for Reasoning over Sequences

Recently Graph Neural Network (GNN) has been applied successfully to var...

Please sign up or login with your details

Forgot password? Click here to reset