Open Relation Modeling: Learning to Define Relations between Entities
This work addresses the challenge of making entity relations more understandable and generalizable for applications in natural language processing and knowledge representation, though it is incremental as it builds on existing pre-trained models.
The paper tackles the problem of generating coherent sentences that describe relations between entities, addressing limitations of existing representations like sentences or knowledge graph facts. The proposed method fine-tunes pre-trained language models with reasoning paths from knowledge graphs, resulting in concise and informative relation descriptions that capture entity characteristics.
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 problem - given two entities, generate a coherent sentence describing the relation between them. To solve this problem, we propose to teach machines to generate definition-like relation descriptions by letting them learn from defining 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. Experimental results show that our model can generate concise but informative relation descriptions that capture the representative characteristics of entities.