English

Efficient long-distance relation extraction with DG-SpanBERT

Computation and Language 2021-02-19 v1 Artificial Intelligence Information Retrieval Machine Learning

Abstract

In natural language processing, relation extraction seeks to rationally understand unstructured text. Here, we propose a novel SpanBERT-based graph convolutional network (DG-SpanBERT) that extracts semantic features from a raw sentence using the pre-trained language model SpanBERT and a graph convolutional network to pool latent features. Our DG-SpanBERT model inherits the advantage of SpanBERT on learning rich lexical features from large-scale corpus. It also has the ability to capture long-range relations between entities due to the usage of GCN on dependency tree. The experimental results show that our model outperforms other existing dependency-based and sequence-based models and achieves a state-of-the-art performance on the TACRED dataset.

Keywords

Cite

@article{arxiv.2004.03636,
  title  = {Efficient long-distance relation extraction with DG-SpanBERT},
  author = {Jun Chen and Robert Hoehndorf and Mohamed Elhoseiny and Xiangliang Zhang},
  journal= {arXiv preprint arXiv:2004.03636},
  year   = {2021}
}
R2 v1 2026-06-23T14:43:24.511Z