# TTM-RE: Memory-Augmented Document-Level Relation Extraction

arXiv: https://arxiv.org/abs/2406.05906 · HTML: https://mlsanity.com/paper/2406.05906/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 9 Jun 2024.

## Builds on (most cited first, 30 of 33)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [Training Language Models with Memory Augmentation](https://mlsanity.com/paper/2205.12674/) (2022)
- [Reasoning with Latent Structure Refinement for Document-Level Relation Extraction](https://mlsanity.com/paper/2005.06312/) (2020)
- [TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task](https://mlsanity.com/paper/2004.14855/) (2020)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [Attention Guided Graph Convolutional Networks for Relation Extraction](https://mlsanity.com/paper/1906.07510/) (2019)
- [Coreferential Reasoning Learning for Language Representation](https://mlsanity.com/paper/2004.06870/) (2020)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs](https://mlsanity.com/paper/1909.00228/) (2019)
- [Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction](https://mlsanity.com/paper/2102.10249/) (2021)
- [Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction](https://mlsanity.com/paper/2205.12696/) (2022)
- [More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction](https://mlsanity.com/paper/2004.03186/) (2020)
- [Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network](https://mlsanity.com/paper/1906.04684/) (2019)
- [Mention Memory: incorporating textual knowledge into Transformers through entity mention attention](https://mlsanity.com/paper/2110.06176/) (2021)
- [Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction](https://mlsanity.com/paper/1802.10569/) (2018)
- [HIN: Hierarchical Inference Network for Document-Level Relation Extraction](https://mlsanity.com/paper/2003.12754/) (2020)
- [Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding](https://mlsanity.com/paper/1911.04910/) (2019)
- [DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction](https://mlsanity.com/paper/2302.08675/) (2023)
- [An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2210.16773/) (2022)
- [With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning](https://mlsanity.com/paper/2308.12383/) (2023)
- [Weakly-supervised Relation Extraction by Pattern-enhanced Embedding Learning](https://mlsanity.com/paper/1711.03226/) (2017)
- [A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genes](https://mlsanity.com/paper/2204.06584/) (2022)
- [A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling](https://mlsanity.com/paper/2210.08709/) (2022)

## Built on by (most cited first, 2 of 2)

- [DOREMI: Optimizing Long Tail Predictions in Document-Level Relation Extraction](https://mlsanity.com/paper/2601.11190/) (2026)
- [Learning What to Remember: Long-horizon Counterfactual Memory Optimization](https://mlsanity.com/paper/2609.37930/) (2026)

## Abstract (arXiv)

Document-level relation extraction aims to categorize the association between any two entities within a document. We find that previous methods for document-level relation extraction are ineffective in exploiting the full potential of large amounts of training data with varied noise levels. For example, in the ReDocRED benchmark dataset, state-of-the-art methods trained on the large-scale, lower-quality, distantly supervised training data generally do not perform better than those trained solely on the smaller, high-quality, human-annotated training data. To unlock the full potential of large-scale noisy training data for document-level relation extraction, we propose TTM-RE, a novel approach that integrates a trainable memory module, known as the Token Turing Machine, with a noisy-robust loss function that accounts for the positive-unlabeled setting. Extensive experiments on ReDocRED, a benchmark dataset for document-level relation extraction, reveal that TTM-RE achieves state-of-the-art performance (with an absolute F1 score improvement of over 3%). Ablation studies further illustrate the superiority of TTM-RE in other domains (the ChemDisGene dataset in the biomedical domain) and under highly unlabeled settings.