Entity, Relation, and Event Extraction with Contextualized Span Representations
This work addresses the challenge of integrating multiple information extraction tasks into a single model for researchers and practitioners in natural language processing, though it is incremental as it builds on existing span-based and contextualized embedding methods.
The paper tackles the problem of unifying named entity recognition, relation extraction, and event extraction by proposing DyGIE++, a multi-task framework that uses contextualized span representations to capture local and global context, achieving state-of-the-art results on four datasets from various domains.
We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by enumerating, refining, and scoring text spans designed to capture local (within-sentence) and global (cross-sentence) context. Our framework achieves state-of-the-art results across all tasks, on four datasets from a variety of domains. We perform experiments comparing different techniques to construct span representations. Contextualized embeddings like BERT perform well at capturing relationships among entities in the same or adjacent sentences, while dynamic span graph updates model long-range cross-sentence relationships. For instance, propagating span representations via predicted coreference links can enable the model to disambiguate challenging entity mentions. Our code is publicly available at https://github.com/dwadden/dygiepp and can be easily adapted for new tasks or datasets.