Unit:
Κατεύθυνση Μεγάλα Δεδομένα και Τεχνητή ΝοημοσύνηΠληροφορική
Supervisors info:
Γεωργία Κούτρικα, Διευθύντρια Έρευνας, Ερευνητικό Κέντρο Αθηνά
Original Title:
Towards more robust text-to-SQL translation
Translated title:
Towards more robust text-to-SQL translation
Summary:
Despite being a fast-paced research field, text-to-SQL systems face critical challenges. The datasets used for the training and evaluation of these systems play a vital role in determining their performance as well as the progress in the field. In this work, we introduce a methodology for text-to-SQL dataset analysis, and we perform an in-depth analysis of several text-to-SQL datasets, providing valuable insights into their capabilities and limitations and how they affect training and evaluation of text-to-SQL systems. We investigate existing evaluation methods, and propose an informative system evaluation based on error analysis. We show how our dataset analysis can help explain the behavior of a system on different datasets. Using our error analysis, we further show how we can pinpoint the sources of errors of a text-to-SQL system for a particular dataset and reveal opportunities for system improvements.
Main subject category:
Technology - Computer science
Keywords:
Machine Translation, Deep Learning, Semantic Parsing, Databases
File:
File access is restricted until 2024-12-13.
Thesis_Mitsopoulou.pdf
2 MB
File access is restricted until 2024-12-13.