Text-to-SQL Oriented to the Process Mining Domain: A PT-EN Dataset for Query Translation
It addresses the challenge of natural language querying for databases in process mining, increasing accessibility for non-experts, but is incremental as it focuses on creating a dataset rather than a new method.
This paper tackles the problem of text-to-SQL conversion in the process mining domain by introducing a bilingual Portuguese-English dataset, text-2-SQL-4-PM, comprising 1,655 natural language utterances and 205 SQL statements, with a baseline study using GPT-3.5 Turbo demonstrating its feasibility.
This paper introduces text-2-SQL-4-PM, a bilingual (Portuguese-English) benchmark dataset designed for the text-to-SQL task in the process mining domain. Text-to-SQL conversion facilitates natural language querying of databases, increasing accessibility for users without SQL expertise and productivity for those that are experts. The text-2-SQL-4-PM dataset is customized to address the unique challenges of process mining, including specialized vocabularies and single-table relational structures derived from event logs. The dataset comprises 1,655 natural language utterances, including human-generated paraphrases, 205 SQL statements, and ten qualifiers. Methods include manual curation by experts, professional translations, and a detailed annotation process to enable nuanced analyses of task complexity. Additionally, a baseline study using GPT-3.5 Turbo demonstrates the feasibility and utility of the dataset for text-to-SQL applications. The results show that text-2-SQL-4-PM supports evaluation of text-to-SQL implementations, offering broader applicability for semantic parsing and other natural language processing tasks.