Two-Phase Hypergraph Based Reasoning with Dynamic Relations for Multi-Hop KBQA

By Guanhua Chen, Yun Chen, Yong Wang, V. Li. 2020

102 citations recorded by the source corpus.

Multi-hop knowledge base question answering (KBQA) aims at finding the answers to a factoid question by reasoning across multiple triples. Note that when human performs multi-hop reasoning, one tends to concentrate on specific relation at different hops and pinpoint a group of entities connected by the relation. Hypergraph convolutional networks (HGCN) can simulate this behavior by leveraging hyperedges to connect more than two nodes more than pairwise connection. However, HGCN is for undirected graphs and does not consider the direction of information transmission. We introduce the directed-HGCN (DHGCN) to adapt to the knowledge graph with directionality. Inspired by human's hop-by-hop reasoning, we propose an interpretable KBQA model based on DHGCN, namely two-phase hypergraph based reasoning with dynamic relations, which explicitly updates relation information and dynamically pays attention to different relations at different hops. Moreover, the model predicts relations hop-by-hop to generate an intermediate relation path. We conduct extensive experiments on two widely used multi-hop KBQA datasets to prove the effectiveness of our model.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Graph Learning

Eduard H. Hovy

Citations in the corpus

A Survey of Data Augmentation Approaches for NLP (2021, methodology): “Chen et al. (2020a) Investigate a DA method for lexically constraint-aware NMT to construct constraint-aware synthetic training data.”
InFillmore: Frame-Guided Language Generation with Bidirectional Context (2021, background): “Finally, it is possible to satisfy lexical constraints in a soft manner as external memories (Li et al., 2020a, 2019) or constructing constraint-aware training data (Chen et al., 2020).”
Data Augmentation Approaches in Natural Language Processing: A Survey (2021, unknown): “Seq2Seq [28], [29], [85], [108] [13], [84], [109], [110], [83] [85]”
Syntax-Aware Data Augmentation for Neural Machine Translation (2020, methodology): “[41] proposed a method for lexically constrained NMT by packing constraints into the source sentence with a separation symbol.”
Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation (2020, unknown): “Similar simulations with the use of the references have been widely adopted in interactive machine translation (Cheng et al., 2016; Hokamp and Liu, 2017; Post and Vilar, 2018; Chen et al., 2020) but not yet explored in summarization.”