Multi-turn Natural Language to Graph Query Language Translation

TL;DR

This paper introduces a new dataset and baseline methods for multi-turn natural language to graph query translation, addressing the limitations of existing single-turn approaches in complex, interactive scenarios.

Contribution

The paper presents an automated LLM-based method to construct a multi-turn NL2GQL dataset and proposes baseline models for multi-turn translation tasks.

Findings

The MTGQL dataset is constructed from a financial market graph database.

Baseline methods demonstrate the feasibility of multi-turn NL2GQL translation.

The dataset and baselines will facilitate future research in multi-turn query understanding.

Abstract

In recent years, research on transforming natural language into graph query language (NL2GQL) has been increasing. Most existing methods focus on single-turn transformation from NL to GQL. In practical applications, user interactions with graph databases are typically multi-turn, dynamic, and context-dependent. While single-turn methods can handle straightforward queries, more complex scenarios often require users to iteratively adjust their queries, investigate the connections between entities, or request additional details across multiple dialogue turns. Research focused on single-turn conversion fails to effectively address multi-turn dialogues and complex context dependencies. Additionally, the scarcity of high-quality multi-turn NL2GQL datasets further hinders the progress of this field. To address this challenge, we propose an automated method for constructing multi-turn NL2GQL datasets based on Large Language Models (LLMs) , and apply this method to develop the MTGQL dataset, which is constructed from a financial market graph database and will be publicly released for future research. Moreover, we propose three types of baseline methods to assess the effectiveness of multi-turn NL2GQL translation, thereby laying a solid foundation for future research.