# SEE: Syntax-aware Entity Embedding for Neural Relation Extraction

arXiv: https://arxiv.org/abs/1801.03603 · HTML: https://mlsanity.com/paper/1801.03603/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jan 2018.

## Built on by (most cited first, 6 of 6)

- [WebFormer: The Web-page Transformer for Structure Information Extraction](https://mlsanity.com/paper/2202.00217/) (2022)
- [Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings](https://mlsanity.com/paper/2102.01156/) (2021)
- [Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction](https://mlsanity.com/paper/2212.14270/) (2022)
- [Information Discovery in e-Commerce](https://mlsanity.com/paper/2410.05763/) (2024)
- [EGFI: Drug-Drug Interaction Extraction and Generation with Fusion of Enriched Entity and Sentence Information](https://mlsanity.com/paper/2101.09914/) (2021)
- [Few Clean Instances Help Denoising Distant Supervision](https://mlsanity.com/paper/2209.06596/) (2022)

## Abstract (arXiv)

Distant supervised relation extraction is an efficient approach to scale relation extraction to very large corpora, and has been widely used to find novel relational facts from plain text. Recent studies on neural relation extraction have shown great progress on this task via modeling the sentences in low-dimensional spaces, but seldom considered syntax information to model the entities. In this paper, we propose to learn syntax-aware entity embedding for neural relation extraction. First, we encode the context of entities on a dependency tree as sentence-level entity embedding based on tree-GRU. Then, we utilize both intra-sentence and inter-sentence attentions to obtain sentence set-level entity embedding over all sentences containing the focus entity pair. Finally, we combine both sentence embedding and entity embedding for relation classification. We conduct experiments on a widely used real-world dataset and the experimental results show that our model can make full use of all informative instances and achieve state-of-the-art performance of relation extraction.