# Combining Distant and Direct Supervision for Neural Relation Extraction

arXiv: https://arxiv.org/abs/1810.12956 · HTML: https://mlsanity.com/paper/1810.12956/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2018.

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

- [SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts](https://mlsanity.com/paper/2104.08809/) (2021)
- [SENT: Sentence-level Distant Relation Extraction via Negative Training](https://mlsanity.com/paper/2106.11566/) (2021)
- [Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors](https://mlsanity.com/paper/2104.08225/) (2021)
- [HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2202.13352/) (2022)
- [Scoring Edit Impact in Grammatical Error Correction via Embedded Association Graphs](https://mlsanity.com/paper/2604.06573/) (2026)
- [SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text](https://mlsanity.com/paper/2607.21610/) (2026)

## Abstract (arXiv)

In relation extraction with distant supervision, noisy labels make it difficult to train quality models. Previous neural models addressed this problem using an attention mechanism that attends to sentences that are likely to express the relations. We improve such models by combining the distant supervision data with an additional directly-supervised data, which we use as supervision for the attention weights. We find that joint training on both types of supervision leads to a better model because it improves the model's ability to identify noisy sentences. In addition, we find that sigmoidal attention weights with max pooling achieves better performance over the commonly used weighted average attention in this setup. Our proposed method achieves a new state-of-the-art result on the widely used FB-NYT dataset.