An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning
This addresses the problem of extracting relations at the entity level rather than mention level for document-level NLP tasks, though it appears incremental as it builds on existing multi-instance learning and coreference resolution methods.
The authors tackled entity-level relation extraction from documents by proposing a joint model that uses multi-instance learning with global entity and local mention representations, achieving state-of-the-art results on the DocRED dataset and reporting the first entity-level end-to-end results.
We present a joint model for entity-level relation extraction from documents. In contrast to other approaches - which focus on local intra-sentence mention pairs and thus require annotations on mention level - our model operates on entity level. To do so, a multi-task approach is followed that builds upon coreference resolution and gathers relevant signals via multi-instance learning with multi-level representations combining global entity and local mention information. We achieve state-of-the-art relation extraction results on the DocRED dataset and report the first entity-level end-to-end relation extraction results for future reference. Finally, our experimental results suggest that a joint approach is on par with task-specific learning, though more efficient due to shared parameters and training steps.