# Efficient long-distance relation extraction with DG-SpanBERT

arXiv: https://arxiv.org/abs/2004.03636 · HTML: https://mlsanity.com/paper/2004.03636/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 5 of 5)

- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [Re-TACRED: Addressing Shortcomings of the TACRED Dataset](https://mlsanity.com/paper/2104.08398/) (2021)
- [DeepStruct: Pretraining of Language Models for Structure Prediction](https://mlsanity.com/paper/2205.10475/) (2022)
- [Zero-Shot Information Extraction as a Unified Text-to-Triple Translation](https://mlsanity.com/paper/2109.11171/) (2021)
- [Modeling Multi-Granularity Hierarchical Features for Relation Extraction](https://mlsanity.com/paper/2204.04437/) (2022)

## Abstract (arXiv)

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.