论文标题
用于处理SPARQL神经机器翻译中知识库元素的复制机制
A Copy Mechanism for Handling Knowledge Base Elements in SPARQL Neural Machine Translation
论文作者
论文摘要
从英语到SPARQL的神经机器翻译（NMT）模型是SPARQL查询产生的有希望的发展。但是，当前的体系结构无法整合知识库（KB）模式，并在培训期间就看不见的知识资源，类和财产进行问题，从而使它们在培训集中涵盖的主题范围之外无法使用。受自然语言处理任务的性能增长的启发，我们建议将神经SPARQL查询生成的复制机制集成为解决此问题的一种方式。我们通过在两个SEQ2SEQ架构（CNN和Transformers）中添加复制层和动态知识库词汇来说明我们的建议。该层使模型直接从问题中复制KB元素，而不是生成问题。我们在最新数据集上评估了我们的方法，包括引用未知KB元素的数据集并衡量复制仪体系结构的准确性。我们的结果表明，与非复制体系结构相比，所有数据集的性能都大大提高。
Neural Machine Translation (NMT) models from English to SPARQL are a promising development for SPARQL query generation. However, current architectures are unable to integrate the knowledge base (KB) schema and handle questions on knowledge resources, classes, and properties unseen during training, rendering them unusable outside the scope of topics covered in the training set. Inspired by the performance gains in natural language processing tasks, we propose to integrate a copy mechanism for neural SPARQL query generation as a way to tackle this issue. We illustrate our proposal by adding a copy layer and a dynamic knowledge base vocabulary to two Seq2Seq architectures (CNNs and Transformers). This layer makes the models copy KB elements directly from the questions, instead of generating them. We evaluate our approach on state-of-the-art datasets, including datasets referencing unknown KB elements and measure the accuracy of the copy-augmented architectures. Our results show a considerable increase in performance on all datasets compared to non-copy architectures.
