UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering
arXiv:1904.01246
Abstract
In relation extraction for knowledge-based question answering, searching from one entity to another entity via a single relation is called "one hop". In related work, an exhaustive search from all one-hop relations, two-hop relations, and so on to the max-hop relations in the knowledge graph is necessary but expensive. Therefore, the number of hops is generally restricted to two or three. In this paper, we propose UHop, an unrestricted-hop framework which relaxes this restriction by use of a transition-based search framework to replace the relation-chain-based search one. We conduct experiments on conventional 1- and 2-hop questions as well as lengthy questions, including datasets such as WebQSP, PathQuestion, and Grid World. Results show that the proposed framework enables the ability to halt, works well with state-of-the-art models, achieves competitive performance without exhaustive searches, and opens the performance gap for long relation paths.
To appear in NAACL-HLT 2019
References in corpus (8)
- Large-scale Simple Question Answering with Memory Networks
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
- Variational Reasoning for Question Answering with Knowledge Graph
- Get To The Point: Summarization with Pointer-Generator Networks
- DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
- Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering
- An Attention-Based Word-Level Interaction Model: Relation Detection for Knowledge Base Question Answering
- Knowledge Base Relation Detection via Multi-View Matching
Cited by in corpus (4)
- Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
- Attention-based Aspect Reasoning for Knowledge Base Question Answering on Clinical Notes
- Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph
- Plot and Rework: Modeling Storylines for Visual Storytelling