[EDBT2021] Conversational OLAP in Action (Best Demo Award EDBT2021)
Demo Paper presented at EDBT 2021: Conversational OLAP in Action (Best Demo Award) Link to the paper: https://edbt2021proceedings.github.io/docs/p145.pdf 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 demonstration we present COOL, a tool supporting natural language COnversational OLap sessions. COOL interprets and translates a natural language dialogue into an OLAP session that starts with a GPSJ (Generalized Projection, Selection and Join) query. The interpretation relies on a formal grammar and a knowledge base storing metadata from a multidimensional cube. COOL is portable, robust, and requires minimal user intervention. It adopts an n-gram based model and a string similarity function to match known entities in the natural language description. In case of incomplete text description, COOL can obtain the correct query either through automatic inference or through interactions with the user to disambiguate the text. The goal of the demonstration is to let the audience evaluate the usability of COOL and its capabilities in assisting query formulation and ambiguity/error resolution.
![EDBT 2021
Motivation
Goal: query multidimensional cubes through natural language
OLAP provides low-level operators [1]
- Users need to have knowledge on the multidimensional model…
- … or even programming skills
Hand-free interaction can be mandatory [2]
- Analytics in augmented reality or with smart assistants
We introduce COOL (COnversational OLap) [3]
Matteo Francia – University of Bologna 2
Introduction
[1] Panos Vassiliadis, Patrick Marcel, Stefano Rizzi: Beyond roll-up's and drill-down's: An intentional analytics model to reinvent OLAP. Information Systems. (2019)
[2] Matteo Francia, Matteo Golfarelli, Stefano Rizzi: A-BI+: A framework for Augmented Business Intelligence. Information Systems. (2020)
[3] Matteo Francia, Enrico Gallinucci, Matteo Golfarelli: COOL: A Framework for Conversational OLAP. Information Systems. (2021)](data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7)
Recommandé
Recommandé
Contenu connexe
Similaire à [EDBT2021] Conversational OLAP in Action (Best Demo Award EDBT2021)
Similaire à [EDBT2021] Conversational OLAP in Action (Best Demo Award EDBT2021) (20)
Plus de University of Bologna
Plus de University of Bologna (9)
Dernier
Dernier (20)
[EDBT2021] Conversational OLAP in Action (Best Demo Award EDBT2021)
- 1. EDBT 2021 Conversational OLAP in Action Matteo Francia1, Enrico Gallinucci1, Matteo Golfarelli1 1University of Bologna, Italy 24th International Conference on Extending Database Technology (EDBT 2021)
- 2. EDBT 2021 Motivation Goal: query multidimensional cubes through natural language OLAP provides low-level operators [1] - Users need to have knowledge on the multidimensional model… - … or even programming skills Hand-free interaction can be mandatory [2] - Analytics in augmented reality or with smart assistants We introduce COOL (COnversational OLap) [3] Matteo Francia – University of Bologna 2 Introduction [1] Panos Vassiliadis, Patrick Marcel, Stefano Rizzi: Beyond roll-up's and drill-down's: An intentional analytics model to reinvent OLAP. Information Systems. (2019) [2] Matteo Francia, Matteo Golfarelli, Stefano Rizzi: A-BI+: A framework for Augmented Business Intelligence. Information Systems. (2020) [3] Matteo Francia, Enrico Gallinucci, Matteo Golfarelli: COOL: A Framework for Conversational OLAP. Information Systems. (2021)
- 3. EDBT 2021 COOL: architecture Matteo Francia – University of Bologna 3 COOL: overview Automatic KB feeding Manual KB enrichment KB DW Metadata & values Synonyms Offline Online Synonyms Ontology
- 4. EDBT 2021 COOL: architecture Matteo Francia – University of Bologna 4 COOL: overview Speech- to-Text OLAP operator Full query Disambiguation & Enhancement Execution & Visualization Automatic KB feeding Manual KB enrichment Raw text Annotated parse forest Parse tree Metadata & values Synonyms Log Interpretation Offline Online Synonyms Ontology SQL generation SQL Sales by Customer and Month Parse tree Statistics KB DW
- 5. EDBT 2021 COOL: intepretation Matteo Francia – University of Bologna 5 COOL: overview Mea Agg “where” “group by” Attr MC SC GC GPSJ SCA SCN SSC Val Region M1 = avg, UnitSales, where, 2019, group by, T = «return the average sales in 2019 per store region» ⟨GPSJ⟩ ::= ⟨MC⟩⟨GC⟩⟨SC⟩ ⟨MC⟩ ::= (⟨Agg⟩⟨Mea⟩ | ⟨Cnt⟩⟨Fct⟩)+ ⟨GC⟩ ::= “𝑔𝑟𝑜𝑢𝑝 𝑏𝑦” ⟨Attr⟩+ ⟨SC⟩ ::= “𝑤ℎ𝑒𝑟𝑒” ⟨SCA⟩ ⟨SCA⟩ ::= ⟨SCN⟩ “𝑎𝑛𝑑” ⟨SCA⟩ | ⟨SCN⟩ ⟨SCN⟩ ::= “𝑛𝑜𝑡” ⟨SSC⟩ | ⟨SSC⟩ ⟨SSC⟩ ::= ⟨Attr⟩⟨Cop⟩⟨Val⟩ | ⟨Attr⟩⟨Val⟩ | ⟨Val⟩ ⟨Cop⟩ ::= “=” | “<>” | “>” | “<” | “≥” | “≤” ⟨Agg⟩ ::= “𝑠𝑢𝑚” | “𝑎𝑣𝑔” | “𝑚𝑖𝑛” | “𝑚𝑎𝑥” ⟨Cnt⟩ ::= “𝑐𝑜𝑢𝑛𝑡” | “𝑐𝑜𝑢𝑛𝑡 𝑑𝑖𝑠𝑡𝑖𝑛𝑐𝑡” ⟨Fct⟩ ::= Domain-specific facts ⟨Mea⟩ ::= Domain-specific measures ⟨Attr⟩ ::= Domain-specific attributes ⟨Val⟩ ::= Domain-specific values
- 6. EDBT 2021 Experimental Evaluation 40 users with heterogeneous OLAP skills - Asked to translate (Italian) analytic goals into English - Users provided good feedback on the interface... - ... as well as on the interpretation accuracy Matteo Francia – University of Bologna 6 Results Full Query OLAP operator OLAP Familiarity Accuracy Time (s) Accuracy Time (s) Low 0.91 141 0.86 102 High 0.91 97 0.92 71
- 7. EDBT 2021 On Air! 7 Check out the full paper: Matteo Francia, Enrico Gallinucci, Matteo Golfarelli: COOL: A framework for conversational OLAP. Information Systems. (2021, in press)
- 8. EDBT 2021 Questions? Matteo Francia – University of Bologna 8 Thank you.