Large language models as storage for SQL querying

Papotti, Paolo
ICDE 2024, 40th IEEE International Conference on Data Engineering, 13-17 May 2024, Utrecht, Netherlands

Declarative querying is one of the main features behind the popularity of databases. However, SQL can be executed only on structured datasets, leaving out of immediate reach infor-mation in unstructured text. Technologies have been deployed to extract structured data from unstructured text and to model such data in relations or triples, but creating well-formed data from text is still time consuming and error prone.


DOI
Type:
Talk
City:
Utrecht
Date:
2024-05-13
Department:
Data Science
Eurecom Ref:
7688
Copyright:
© 2024 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
See also:

PERMALINK : https://www.eurecom.fr/publication/7688