BioNCERE：面向生物医学文本关系抽取的非对比增强方法
BioNCERE: Non-Contrastive Enhancement For Relation Extraction In Biomedical Texts
AI总结：
针对生物医学关系抽取模型的各向异性问题，提出无需命名实体标签的BioNCERE方法，结合迁移学习与非对比学习分三阶段训练，在SemMedDB上取得接近现有最优的性能，降低了标注成本。
摘要：
生物医学领域关系抽取（RE）的现有最优模型通常采用分类方式微调BioBERT，但可能存在各向异性问题。对比学习方法能够缓解这一现象，还可避免分类任务中的类别坍缩。本文提出一种名为biological non-contrastive relation extraction（BioNCERE，生物非对比关系抽取）的新型训练方法，该方法无需命名实体标签即可完成关系抽取训练，以降低标注成本。BioNCERE结合迁移学习与非对比学习，避免完全坍缩或维度坍缩，同时规避过拟合问题。它通过两次运用迁移学习，分三个阶段解决关系抽取任务：在提出的流水线中冻结前序阶段学习到的权重，并在第二阶段引入非对比学习，使模型无需命名实体知识即可预测关系。在SemMedDB数据集上的实验表明，该方法在不使用命名实体信息的情况下，性能与现有最优关系抽取模型相近。
英文摘要：
State-of-the-art models for relation extraction (RE) in the biomedical domain consider finetuning BioBERT using classification, but they may suffer from the anisotropy problem. Contrastive learning methods can reduce this anisotropy phenomena, and also help to avoid class collapse in any classification problem. In the present paper, a new training method called biological non-contrastive relation extraction (BioNCERE) is introduced for relation extraction without using any named entity labels for training to reduce annotation costs. BioNCERE uses transfer learning and non-contrastive learning to avoid full or dimensional collapse as well as bypass overfitting. It resolves RE in three stages by leveraging transfer learning two times. By freezing the weights learned in previous stages in the proposed pipeline and by leveraging non-contrastive learning in the second stage, the model predicts relations without any knowledge of named entities. Experiments have been done on SemMedDB that are almost similar to State-of-the-art performance on RE without using the information of named entities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
