Open Relation Modeling: Learning to Define Relations between Entities

08/20/2021
by   Jie Huang, et al.
2

Relations between entities can be represented by different instances, e.g., a sentence containing both entities or a fact in a Knowledge Graph (KG). However, these instances may not well capture the general relations between entities, may be difficult to understand by humans, even may not be found due to the incompleteness of the knowledge source. In this paper, we introduce the Open Relation Modeling task - given two entities, generate a coherent sentence describing the relation between them. To solve this task, we propose to teach machines to generate definition-like relation descriptions by letting them learn from definitions of entities. Specifically, we fine-tune Pre-trained Language Models (PLMs) to produce definitions conditioned on extracted entity pairs. To help PLMs reason between entities and provide additional relational knowledge to PLMs for open relation modeling, we incorporate reasoning paths in KGs and include a reasoning path selection mechanism. We show that PLMs can select interpretable and informative reasoning paths by confidence estimation, and the selected path can guide PLMs to generate better relation descriptions. Experimental results show that our model can generate concise but informative relation descriptions that capture the representative characteristics of entities and relations.

READ FULL TEXT
research
05/21/2022

DKG: A Descriptive Knowledge Graph for Explaining Relationships between Entities

In this paper, we propose Descriptive Knowledge Graph (DKG) - an open an...
research
11/20/2022

VER: Learning Natural Language Representations for Verbalizing Entities and Relations

Entities and relationships between entities are vital in the real world....
research
05/18/2022

Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer

Entity Alignment (EA) has attracted widespread attention in both academi...
research
01/04/2023

Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer

Recent studies on knowledge graphs (KGs) show that path-based methods em...
research
01/12/2018

Relational Characterisations of Paths

Binary relations are one of the standard ways to encode, characterise an...
research
12/18/2019

Uncovering Relations for Marketing Knowledge Representation

Online behaviors of consumers and marketers generate massive marketing d...
research
07/05/2016

Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks

Our goal is to combine the rich multistep inference of symbolic logical ...

Please sign up or login with your details

Forgot password? Click here to reset