GenRE: A Generative Model for Relation Extraction

Relation extraction (RE) is an important information extraction task which provides essential information to many NLP applications such as knowledge base population and question answering. In this paper, we present a novel generative model for relation extraction (which we call GenRE), where RE is modeled as a sequence-to-sequence generation task. We explore various encoding schemes for the source and target sequences, and design effective schemes that enable GenRE to achieve state-of-the-art performance on three benchmark RE datasets. In addition, we introduce negative sampling and decoding scaling techniques which provide a flexible tool to tune the precision and recall performance of our GenRE model. Our approach can be extended to extract all relation triples from a sentence in one pass. Although the one-pass approach incurs certain performance loss, it is much more computationally efficient.