A Copy Mechanism for Handling Knowledge Base Elements in SPARQL Neural Machine Translation

TL;DR

This paper introduces a copy mechanism in neural SPARQL translation models, enabling better handling of unseen knowledge base elements by copying from questions, significantly improving accuracy.

Contribution

It proposes a copy layer and dynamic KB vocabulary integration into Seq2Seq models for improved neural SPARQL query generation.

Findings

Significant performance improvement on datasets with unknown KB elements.

Effective integration of copy mechanism into CNNs and Transformers.

Enhanced generalization to unseen knowledge resources.

Abstract

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.