@inproceedings{OpitzHochgeschwender2022, author = {Dominik Opitz and Nico Hochgeschwender}, title = {From Zero to Hero: Generating Training Data for Question-To-Cypher Models}, series = {2022 IEEE/ACM 1st International Workshop on Natural Language-Based Software Engineering (NLBSE), Pittsburgh, PA, USA, 8 May 2022}, publisher = {Association for Computing Machinery}, isbn = {978-1-4503-9343-0}, doi = {10.1145/3528588.3528655}, pages = {17 -- 20}, year = {2022}, abstract = {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.}, language = {en} }