GLiREL -- Generalist Model for Zero-Shot Relation Extraction
This addresses the problem of extracting relationships between entities without labeled training data for specific relations, which is incremental as it builds on recent zero-shot named entity recognition advancements.
The paper tackles zero-shot relation extraction by introducing GLiREL, a lightweight model that predicts relationship labels between multiple entities in a single forward pass, achieving state-of-the-art results on FewRel and WikiZSL benchmarks.
We introduce GLiREL (Generalist Lightweight model for zero-shot Relation Extraction), an efficient architecture and training paradigm for zero-shot relation classification. Inspired by recent advancements in zero-shot named entity recognition, this work presents an approach to efficiently and accurately predict zero-shot relationship labels between multiple entities in a single forward pass. Experiments using the FewRel and WikiZSL benchmarks demonstrate that our approach achieves state-of-the-art results on the zero-shot relation classification task. In addition, we contribute a protocol for synthetically-generating datasets with diverse relation labels.