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.

大规模嘈杂训练数据中的文档级关系抽取问题是一个具有挑战性的领域，本研究提出了一种集成可训练内存模块（Token Turing Machine）和嘈杂鲁棒性损失函数的新方法 TTM-RE，通过在 ReDocRED 基准数据集上进行广泛实验，实现了最先进的性能表现（F1 得分提高了 3% 以上），并在其他领域（如生物医学领域的 ChemDisGene 数据集）和高度未标记的情境下展现了 TTM-RE 的优越性.