Open Relation Modeling: Learning to Define Relations between Entities
Open Relation Modeling: Learning to Define Relations between Entities
复制标题
DOI：
10.18653/v1/2022.findings-acl.26
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Jie Huang;K. Chang;Jinjun Xiong;Wen-mei W. Hwu
中科院分区：
文献类型：
--
作者：
Jie Huang;K. Chang;Jinjun Xiong;Wen-mei W. Hwu
实体之间的关系可以由不同的实例来表示，例如，包含两个实体的句子或知识图(KG)中的事实。然而，这些实例可能不能很好地捕捉实体之间的一般关系，可能难以被人类理解，甚至可能由于知识源的不完整性而无法找到。在本文中，我们引入了开放关系建模问题--给定两个实体，生成一个描述它们之间关系的连贯语句。为了解决这个问题，我们建议教机器通过让它们从定义实体中学习来生成类似定义的关系描述。具体地说，我们微调预训练的语言模型(PLM)，以产生以提取的实体对为条件的定义。为了帮助PLM在实体之间进行推理，并为PLM提供额外的关系知识以进行开放关系建模，我们在KGS中加入了推理路径，并包括推理路径选择机制。实验结果表明，该模型能够生成简明而信息丰富的关系描述，能够很好地反映实体的典型特征。
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.