Work

Span-Based Joint Entity and Relation Extraction with Transformer Pre-Training

Year: 2020
Type: book-chapter
Abstract: 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.
Language: English
Open Access status: hybrid
OpenAlex ID: W2974004142
FWCI: 92.36
Cites: 46
Cited by: 640
Related to: 10