Span-based Joint Entity and Relation Extraction with Transformer Pre-training
This addresses the problem of extracting entities and their relations from text for NLP applications, representing an incremental advance in joint extraction methods.
The paper tackles joint entity and relation extraction by introducing SpERT, a span-based attention model that uses BERT embeddings and strong negative sampling, achieving up to 2.6% F1 score improvement over prior work on several datasets.
We introduce SpERT, an attention model for span-based joint entity and relation extraction. Our key contribution is a light-weight reasoning on BERT embeddings, which features entity recognition and filtering, as well as relation classification with a localized, marker-free context representation. The model is trained using strong within-sentence negative samples, which are efficiently extracted in a single BERT pass. These aspects facilitate a search over all spans in the sentence. In ablation studies, we demonstrate the benefits of pre-training, strong negative sampling and localized context. Our model outperforms prior work by up to 2.6% F1 score on several datasets for joint entity and relation extraction.