$R^3$-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Yuhang, He, Yu, Tian, Siyu, Ni, Yuchen, Yin, Zhangyue, Liu, Xiang, Ji, Chuanjun, Liu, Sen, Qiu, Xipeng, Ye, Guangnan, Chai, Hongfeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913411068067840
author Zhou, Yuhang
He, Yu
Tian, Siyu
Ni, Yuchen
Yin, Zhangyue
Liu, Xiang
Ji, Chuanjun
Liu, Sen
Qiu, Xipeng
Ye, Guangnan
Chai, Hongfeng
author_facet Zhou, Yuhang
He, Yu
Tian, Siyu
Ni, Yuchen
Yin, Zhangyue
Liu, Xiang
Ji, Chuanjun
Liu, Sen
Qiu, Xipeng
Ye, Guangnan
Chai, Hongfeng
contents 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, $R^3$-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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_01862
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle $R^3$-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL
Zhou, Yuhang
He, Yu
Tian, Siyu
Ni, Yuchen
Yin, Zhangyue
Liu, Xiang
Ji, Chuanjun
Liu, Sen
Qiu, Xipeng
Ye, Guangnan
Chai, Hongfeng
Computation and Language
Databases
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, $R^3$-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.
title $R^3$-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL
topic Computation and Language
Databases
url https://arxiv.org/abs/2311.01862