Learning Relation Entailment with Structured and Textual Information

Zhengbao Jiang, Jun Araki, Donghan Yu, Ruohong Zhang, Wei Xu, Yiming Yang, Graham Neubig

Keywords: relation entailment, structured information, textual information

TL;DR: Learning to predict relation entailment using both structured and textual information

Subject Areas: Knowledge Representation, Semantic Web and Search, Information Extraction, Machine Learning

Abstract: Relations among words and entities are important for semantic understanding of text, but previous work has largely not considered relations between relations, or meta-relations. In this paper, we specifically examine relation entailment, where the existence of one relation can entail the existence of another relation. Relation entailment allows us to construct relation hierarchies, enabling applications in representation learning, question answering, relation extraction, and summarization. To this end, we formally define the new task of predicting relation entailment and construct a dataset by expanding the existing Wikidata relation hierarchy without expensive human intervention. We propose several methods that incorporate both structured and textual information to represent relations for this task. Experiments and analysis demonstrate that this task is challenging, and we provide insights into task characteristics that may form a basis for future work. The dataset and code have been released at https://github.com/jzbjyb/RelEnt.

Archival Status: Archival