论文标题
通过模板填充的零射击三重提取
Zero-shot Triplet Extraction by Template Infilling
论文作者
论文摘要
三胞胎提取的任务旨在从非结构化文本中提取成对的实体及其相应的关系。大多数现有方法在涉及特定目标关系的培训数据上训练提取模型，并且无法提取在训练时未观察到的新关系。概括模型以看不见的关系通常需要对通常嘈杂且不可靠的合成训练数据进行微调。我们表明，通过将三重态提取到模板填充任务（LM）上，我们可以为提取模型配备零拍的学习能力，并消除对其他培训数据的需求。我们提出了一个新颖的框架ZETT（通过模板填充的零击三重提取），该框架将任务目标与生成变压器的训练前目标保持一致，以概括不见的关系。在少数和Wiki-ZSL数据集上进行的实验表明，即使使用自动生成的模板，Zett也表现出一致且稳定的性能，超过了先前的最新方法。 https://github.com/megagonlabs/zett/
The task of triplet extraction aims to extract pairs of entities and their corresponding relations from unstructured text. Most existing methods train an extraction model on training data involving specific target relations, and are incapable of extracting new relations that were not observed at training time. Generalizing the model to unseen relations typically requires fine-tuning on synthetic training data which is often noisy and unreliable. We show that by reducing triplet extraction to a template infilling task over a pre-trained language model (LM), we can equip the extraction model with zero-shot learning capabilities and eliminate the need for additional training data. We propose a novel framework, ZETT (ZEro-shot Triplet extraction by Template infilling), that aligns the task objective to the pre-training objective of generative transformers to generalize to unseen relations. Experiments on FewRel and Wiki-ZSL datasets demonstrate that ZETT shows consistent and stable performance, outperforming previous state-of-the-art methods, even when using automatically generated templates. https://github.com/megagonlabs/zett/
