Span-based Joint Entity and Relation Extraction with Transformer Pre-training

By Markus Eberts, Adrian Ulges. European Conference on Artificial Intelligence, 2019

479 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/360d36899dbd44109f5040251cee35822900edb9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Structured Prediction as Translation between Augmented Natural Languages (2021, methodology): “TANL performs better than SpERT with fewer data, especially on the more complex task of relation extraction (right plot).”