Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Su, Chang, Qi, Jiexing, Yan, He, Zou, Kai, Lin, Zhouhan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.05731
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914967877320704
author Su, Chang
Qi, Jiexing
Yan, He
Zou, Kai
Lin, Zhouhan
author_facet Su, Chang
Qi, Jiexing
Yan, He
Zou, Kai
Lin, Zhouhan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05731
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training
Su, Chang
Qi, Jiexing
Yan, He
Zou, Kai
Lin, Zhouhan
Information Retrieval
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.
title Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training
topic Information Retrieval
url https://arxiv.org/abs/2410.05731