UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering
Zi-Yuan Chen, Chih-Hung Chang, Yi-Pei Chen, Jijnasa Nayak, Lun-Wei Ku

TL;DR
UHop introduces an unrestricted-hop relation extraction framework for knowledge-based question answering, enabling flexible relation path searches beyond fixed hop limits, improving performance especially on long relation paths.
Contribution
The paper presents UHop, a novel transition-based search framework that relaxes hop restrictions in relation extraction, allowing for more flexible and efficient knowledge graph traversal.
Findings
Enables relation extraction with variable hop lengths.
Works well with state-of-the-art models.
Achieves competitive performance without exhaustive search.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Advanced Graph Neural Networks
