The democratization of data access and the adoption of OLAP in scenarios requiring hand-free interfaces push towards the creation of smart OLAP interfaces. In this paper, we introduce COOL, a framework devised for COnversational OLap applications. COOL interprets and translates a natural language dialog into an OLAP session that starts with a GPSJ (Generalized Projection, Selection, and Join) query and continues with the application of OLAP operators. The interpretation relies on a formal grammar and on a repository storing metadata and values from a multidimensional cube. In case of ambiguous or incomplete text description, COOL can obtain the correct query either through automatic inference or user interactions to disambiguate the text. Our tests show very promising results in terms of effectiveness, efficiency, and user experience. Besides adding novel support to the interpretation and translation of complete analytical OLAP sessions, COOL achieves an average accuracy of 94% in the interpretation of GPSJ queries from real datasets.

COOL: A framework for conversational OLAP / Francia M.; Gallinucci E.; Golfarelli M.. - In: INFORMATION SYSTEMS. - ISSN 0306-4379. - ELETTRONICO. - 104:(2022), pp. 101752.1-101752.18. [10.1016/j.is.2021.101752]

COOL: A framework for conversational OLAP

Francia M.;Gallinucci E.;Golfarelli M.
2022

Abstract

The democratization of data access and the adoption of OLAP in scenarios requiring hand-free interfaces push towards the creation of smart OLAP interfaces. In this paper, we introduce COOL, a framework devised for COnversational OLap applications. COOL interprets and translates a natural language dialog into an OLAP session that starts with a GPSJ (Generalized Projection, Selection, and Join) query and continues with the application of OLAP operators. The interpretation relies on a formal grammar and on a repository storing metadata and values from a multidimensional cube. In case of ambiguous or incomplete text description, COOL can obtain the correct query either through automatic inference or user interactions to disambiguate the text. Our tests show very promising results in terms of effectiveness, efficiency, and user experience. Besides adding novel support to the interpretation and translation of complete analytical OLAP sessions, COOL achieves an average accuracy of 94% in the interpretation of GPSJ queries from real datasets.
2022
COOL: A framework for conversational OLAP / Francia M.; Gallinucci E.; Golfarelli M.. - In: INFORMATION SYSTEMS. - ISSN 0306-4379. - ELETTRONICO. - 104:(2022), pp. 101752.1-101752.18. [10.1016/j.is.2021.101752]
Francia M.; Gallinucci E.; Golfarelli M.
File in questo prodotto:
File Dimensione Formato  
IS_2020_COOL.pdf

Open Access dal 23/02/2024

Tipo: Postprint
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione - Non commerciale - Non opere derivate (CCBYNCND)
Dimensione 2.73 MB
Formato Adobe PDF
2.73 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/845493
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 6
social impact