# How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction

arXiv: https://arxiv.org/abs/2107.12064 · HTML: https://mlsanity.com/paper/2107.12064/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 26 Jul 2021.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Learning from Context or Names? An Empirical Study on Neural Relation Extraction](https://mlsanity.com/paper/2010.01923/) (2020)
- [Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks](https://mlsanity.com/paper/1903.01306/) (2019)
- [Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention](https://mlsanity.com/paper/1804.06987/) (2018)
- [Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions](https://mlsanity.com/paper/1904.00143/) (2019)
- [Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/1911.11899/) (2019)
- [Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/1809.00699/) (2018)
- [Relation Extraction with Explanation](https://mlsanity.com/paper/2005.14271/) (2020)

## Built on by (most cited first, 8 of 8)

- [Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion](https://mlsanity.com/paper/2108.01387/) (2021)
- [An Overview of Distant Supervision for Relation Extraction with a Focus on Denoising and Pre-training Methods](https://mlsanity.com/paper/2207.08286/) (2022)
- [Analogical Inference Enhanced Knowledge Graph Embedding](https://mlsanity.com/paper/2301.00982/) (2023)
- [TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation](https://mlsanity.com/paper/2306.14580/) (2023)
- [Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2211.01432/) (2022)
- [Mitigating Heterogeneity among Factor Tensors via Lie Group Manifolds for Tensor Decomposition Based Temporal Knowledge Graph Embedding](https://mlsanity.com/paper/2404.09155/) (2024)
- [SCoRE: Streamlined Corpus-based Relation Extraction using Multi-Label Contrastive Learning and Bayesian kNN](https://mlsanity.com/paper/2507.06895/) (2025)
- [Biquaternionic Space with Complex-valued Attention for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2609.14279/) (2026)

## Abstract (arXiv)

Knowledge Graph (KG) and attention mechanism have been demonstrated effective in introducing and selecting useful information for weakly supervised methods. However, only qualitative analysis and ablation study are provided as evidence. In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE). We find that (1) higher attention accuracy may lead to worse performance as it may harm the model's ability to extract entity mention features; (2) the performance of attention is largely influenced by various noise distribution patterns, which is closely related to real-world datasets; (3) KG-enhanced attention indeed improves RE performance, while not through enhanced attention but by incorporating entity prior; and (4) attention mechanism may exacerbate the issue of insufficient training data. Based on these findings, we show that a straightforward variant of RE model can achieve significant improvements (6% AUC on average) on two real-world datasets as compared with three state-of-the-art baselines. Our codes and datasets are available at https://github.com/zig-kwin-hu/how-KG-ATT-help.