Simple BERT Models for Relation Extraction and Semantic Role Labeling
Abstract
We present simple BERT-based models for relation extraction and semantic role labeling. In recent years, state-of-the-art performance has been achieved using neural models by incorporating lexical and syntactic features such as part-of-speech tags and dependency trees. In this paper, extensive experiments on datasets for these two tasks show that without using any external features, a simple BERT-based model can achieve state-of-the-art performance. To our knowledge, we are the first to successfully apply BERT in this manner. Our models provide strong baselines for future research.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2019
- DOI:
- 10.48550/arXiv.1904.05255
- arXiv:
- arXiv:1904.05255
- Bibcode:
- 2019arXiv190405255S
- Keywords:
-
- Computer Science - Computation and Language
- E-Print:
- work in progress