论文标题
说唱：一种新颖的几杆关系提取管道，并具有查询信息引导注意力和自适应原型融合
RAPS: A Novel Few-Shot Relation Extraction Pipeline with Query-Information Guided Attention and Adaptive Prototype Fusion
论文作者
论文摘要
很少有射击关系提取（FSRE）旨在通过仅仅用少数注释的实例学习来识别看不见的关系。为了更有效地推广到新的关系，本文提出了基于查询信息的FSRE任务的新管道，引导着注意力和自适应原型融合，即说唱。具体而言，RAPS首先通过查询信息引导的注意模块得出了关系原型，该模块在支持实例和查询实例之间利用了丰富的交互式信息，以获得更准确的初始原型表示。然后，Raps详细地将派生的初始原型与自适应原型融合机制相结合，以获取用于训练和预测的集成原型。基准数据集中的实验很少1.0显示了我们针对最先进方法的方法的显着改善。
Few-shot relation extraction (FSRE) aims at recognizing unseen relations by learning with merely a handful of annotated instances. To generalize to new relations more effectively, this paper proposes a novel pipeline for the FSRE task based on queRy-information guided Attention and adaptive Prototype fuSion, namely RAPS. Specifically, RAPS first derives the relation prototype by the query-information guided attention module, which exploits rich interactive information between the support instances and the query instances, in order to obtain more accurate initial prototype representations. Then RAPS elaborately combines the derived initial prototype with the relation information by the adaptive prototype fusion mechanism to get the integrated prototype for both train and prediction. Experiments on the benchmark dataset FewRel 1.0 show a significant improvement of our method against state-of-the-art methods.
