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

TL;DR

The paper introduces BAG, a novel bi-directional attention entity graph convolutional network designed for multi-hop reasoning question answering, effectively capturing relationships between entities and queries to improve accuracy.

Contribution

It proposes a new model combining entity graphs, graph convolution, and bidirectional attention for enhanced multi-hop reasoning in QA tasks.

Findings

Achieves state-of-the-art accuracy on QAngaroo WIKIHOP dataset.

Effectively models entity relationships and query interactions.

Outperforms existing methods in multi-hop reasoning accuracy.

Abstract

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.