# SENT: Sentence-level Distant Relation Extraction via Negative Training

arXiv: https://arxiv.org/abs/2106.11566 · HTML: https://mlsanity.com/paper/2106.11566/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 60 references that are in the map.
- First posted on arXiv 22 Jun 2021.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Decoupling "when to update" from "how to update"](https://mlsanity.com/paper/1706.02613/) (2017)
- [Are Anchor Points Really Indispensable in Label-Noise Learning?](https://mlsanity.com/paper/1906.00189/) (2019)
- [NLNL: Negative Learning for Noisy Labels](https://mlsanity.com/paper/1908.07387/) (2019)
- [Curriculum Loss: Robust Learning and Generalization against Label Corruption](https://mlsanity.com/paper/1905.10045/) (2019)
- [Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks](https://mlsanity.com/paper/1903.01306/) (2019)
- [RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information](https://mlsanity.com/paper/1812.04361/) (2018)
- [Reinforcement Learning for Relation Classification from Noisy Data](https://mlsanity.com/paper/1808.08013/) (2018)
- [Question Answering on Freebase via Relation Extraction and Textual Evidence](https://mlsanity.com/paper/1603.00957/) (2016)
- [Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction](https://mlsanity.com/paper/1906.08646/) (2019)
- [Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning](https://mlsanity.com/paper/1805.09927/) (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)
- [Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix](https://mlsanity.com/paper/1705.03995/) (2017)
- [Multilingual Relation Extraction using Compositional Universal Schema](https://mlsanity.com/paper/1511.06396/) (2015)
- [Are Noisy Sentences Useless for Distant Supervised Relation Extraction?](https://mlsanity.com/paper/1911.09788/) (2019)
- [Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction](https://mlsanity.com/paper/1812.10604/) (2018)
- [Combining Distant and Direct Supervision for Neural Relation Extraction](https://mlsanity.com/paper/1810.12956/) (2018)
- [Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding](https://mlsanity.com/paper/1812.09516/) (2018)
- [Structured Minimally Supervised Learning for Neural Relation Extraction](https://mlsanity.com/paper/1904.00118/) (2019)
- [Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction](https://mlsanity.com/paper/1909.06007/) (2019)
- [Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training](https://mlsanity.com/paper/1805.10959/) (2018)
- [Uncover the Ground-Truth Relations in Distant Supervision: A Neural Expectation-Maximization Framework](https://mlsanity.com/paper/1909.05448/) (2019)

## Built on by (most cited first, 10 of 10)

- [What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification](https://mlsanity.com/paper/2204.13516/) (2022)
- [HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2202.13352/) (2022)
- [Uncertainty Guided Label Denoising for Document-level Distant Relation Extraction](https://mlsanity.com/paper/2305.11029/) (2023)
- [Diversifying Neural Dialogue Generation via Negative Distillation](https://mlsanity.com/paper/2205.02795/) (2022)
- [Handling Realistic Label Noise in BERT Text Classification](https://mlsanity.com/paper/2305.16337/) (2023)
- [Improving Distantly Supervised Relation Extraction by Natural Language Inference](https://mlsanity.com/paper/2208.00346/) (2022)
- [Rank-Aware Negative Training for Semi-Supervised Text Classification](https://mlsanity.com/paper/2306.07621/) (2023)
- [Distantly-Supervised Joint Extraction with Noise-Robust Learning](https://mlsanity.com/paper/2310.04994/) (2023)
- [Open Set Relation Extraction via Unknown-Aware Training](https://mlsanity.com/paper/2306.04950/) (2023)
- [KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2406.16374/) (2024)

## Abstract (arXiv)

Distant supervision for relation extraction provides uniform bag labels for each sentence inside the bag, while accurate sentence labels are important for downstream applications that need the exact relation type. Directly using bag labels for sentence-level training will introduce much noise, thus severely degrading performance. In this work, we propose the use of negative training (NT), in which a model is trained using complementary labels regarding that ``the instance does not belong to these complementary labels". Since the probability of selecting a true label as a complementary label is low, NT provides less noisy information. Furthermore, the model trained with NT is able to separate the noisy data from the training data. Based on NT, we propose a sentence-level framework, SENT, for distant relation extraction. SENT not only filters the noisy data to construct a cleaner dataset, but also performs a re-labeling process to transform the noisy data into useful training data, thus further benefiting the model's performance. Experimental results show the significant improvement of the proposed method over previous methods on sentence-level evaluation and de-noise effect.