Volltext-Downloads (blau) und Frontdoor-Views (grau)

From Zero to Hero: Generating Training Data for Question-To-Cypher Models

  • Graph databases employ graph structures such as nodes, attributes and edges to model and store relationships among data. To access this data, graph query languages (GQL) such as Cypher are typically used, which might be difficult to master for end-users. In the context of relational databases, sequence to SQL models, which translate natural language questions to SQL queries, have been proposed. While these Neural Machine Translation (NMT) models increase the accessibility of relational databases, NMT models for graph databases are not yet available mainly due to the lack of suitable parallel training data. In this short paper we sketch an architecture which enables the generation of synthetic training data for the graph query language Cypher.

Export metadata

Additional Services

Search Google Scholar Check availability


Show usage statistics
Document Type:Conference Object
Author:Dominik Opitz, Nico Hochgeschwender
Parent Title (English):2022 IEEE/ACM 1st International Workshop on Natural Language-Based Software Engineering (NLBSE), Pittsburgh, PA, USA, 8 May 2022
First Page:17
Last Page:20
Publisher:Association for Computing Machinery
Date of first publication:2022/06/30
Copyright:© 2022 Association for Computing Machinery. Abstracting with credit is permitted.
Funding:This research was partially funded by EU SESAME project (ID: 101017258) and DLR OpenSearch.
Keyword:Cypher; Data Generation; Machine Learning; Neural Machine Translation; SQL
Departments, institutes and facilities:Fachbereich Informatik
Institut für Cyber Security & Privacy (ICSP)
Projects:SESAME Secure and Safe Multi-Robot Systems (EC/H2020/101017258)
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Entry in this database:2022/07/18