R3-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL
Yuhang Zhou, Yu He, Siyu Tian, Yuchen Ni, Zhangyue Yin, Xiang Liu, Chuanjun Ji, Sen Liu
Abstract
While current tasks of converting natural language to SQL (NL2SQL) using Foundation Models have shown impressive achievements, adapting these approaches for converting natural language to Graph Query Language (NL2GQL) encounters hurdles due to the distinct nature of GQL compared to SQL, alongside the diverse forms of GQL. Moving away from traditional rule-based and slot-filling methodologies, we introduce a novel approach, R3-NL2GQL, integrating both small and large Foundation Models for ranking, rewriting, and refining tasks. This method leverages the interpretative strengths of smaller models for initial ranking and rewriting stages, while capitalizing on the superior generalization and query generation prowess of larger models for the final transformation of natural language queries into GQL formats. Addressing the scarcity of datasets in this emerging field, we have developed a bilingual dataset, sourced from graph database manuals and selected open-source Knowledge Graphs (KGs). Our evaluation of this methodology on this dataset demonstrates its promising efficacy and robustness.
BibTeX
@inproceedings{zhou-etal-2024-r3,
title = "$R^3$-{NL}2{GQL}: A Model Coordination and Knowledge Graph Alignment Approach for {NL}2{GQL}",
author = "Zhou, Yuhang and
He, Yu and
Tian, Siyu and
Ni, Yuchen and
Yin, Zhangyue and
Liu, Xiang and
Ji, Chuanjun and
Liu, Sen and
Qiu, Xipeng and
Ye, Guangnan and
Chai, Hongfeng",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.800/",
doi = "10.18653/v1/2024.findings-emnlp.800",
pages = "13679--13692"
}