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 accessability 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.
Sun 8 MayDisplayed time zone: Eastern Time (US & Canada) change
08:30 - 09:40 | Paper Session 1NLBSE at NLBSE room Chair(s): Andrea Di Sorbo University of Sannio, Sebastiano Panichella Zurich University of Applied Sciences | ||
08:30 20mTalk | Unsupervised Extreme Multi Label Classification of Stack Overflow Posts NLBSE | ||
08:50 20mTalk | Understanding Digits in Identifier Names: An Exploratory Study NLBSE Anthony Peruma Rochester Institute of Technology, Christian D. Newman Rochester Institute of Technology Pre-print Media Attached | ||
09:10 15mTalk | From Zero to Hero: Generating Training Data for Question-To-Cypher Models NLBSE | ||
09:25 15mTalk | Automatic Identification of Informative Code in Stack Overflow Posts NLBSE Preetha Chatterjee Drexel University, USA | ||