# Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training

Source: [Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training](<https://www.sota2.com/research/paper/68fa75221e209131cea660c5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:27:16.108Z

Authors: Chang Su, Jiexing Qi, He Yan, Kai Zou, Zhouhan Lin

Published: 2024-10-08T06:48:46.000Z

## Abstract

Semantic parsing that translates natural language queries to SPARQL is of great importance for Knowledge Graph Question Answering (KGQA) systems. Although pre-trained language models like T5 have achieved significant success in the Text-to-SPARQL task, their generated outputs still exhibit notable errors specific to the SPARQL language, such as triplet flips. To address this challenge and further improve the performance, we propose an additional pre-training stage with a new objective, Triplet Order Correction (TOC), along with the commonly used Masked Language Modeling (MLM), to collectively enhance the model's sensitivity to triplet order and SPARQL syntax. Our method achieves state-of-the-art performances on three widely-used benchmarks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.05731>)

[PDF](<https://arxiv.org/pdf/2410.05731.pdf>)
