# Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction

arXiv: https://arxiv.org/abs/1903.10126 · HTML: https://mlsanity.com/paper/1903.10126/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2019.

## Built on by (most cited first, 9 of 9)

- [Multimodal Learning on Graphs for Disease Relation Extraction](https://mlsanity.com/paper/2203.08893/) (2022)
- [KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction](https://mlsanity.com/paper/2106.00459/) (2021)
- [Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors](https://mlsanity.com/paper/2104.08225/) (2021)
- [Multi-view Inference for Relation Extraction with Uncertain Knowledge](https://mlsanity.com/paper/2104.13579/) (2021)
- [Question Answering with Deep Neural Networks for Semi-Structured Heterogeneous Genealogical Knowledge Graphs](https://mlsanity.com/paper/2307.16214/) (2023)
- [ASPER: Attention-based Approach to Extract Syntactic Patterns denoting Semantic Relations in Sentential Context](https://mlsanity.com/paper/2104.01523/) (2021)
- [Relation Extraction Across Entire Books to Reconstruct Community Networks: The AffilKG Datasets](https://mlsanity.com/paper/2505.10798/) (2025)
- [REMOD: Relation Extraction for Modeling Online Discourse](https://mlsanity.com/paper/2102.11105/) (2021)
- [Knowledge-Enhanced Relation Extraction Dataset](https://mlsanity.com/paper/2210.11231/) (2022)

## Abstract (arXiv)

Knowledge Bases (KBs) require constant up-dating to reflect changes to the world they represent. For general purpose KBs, this is often done through Relation Extraction (RE), the task of predicting KB relations expressed in text mentioning entities known to the KB. One way to improve RE is to use KB Embeddings (KBE) for link prediction. However, despite clear connections between RE and KBE, little has been done toward properly unifying these models systematically. We help close the gap with a framework that unifies the learning of RE and KBE models leading to significant improvements over the state-of-the-art in RE. The code is available at https://github.com/billy-inn/HRERE.