Quelo is a formal framework and a tool supporting the user in the task of formulating a precise query – which best captures her information needs – even in the case of complete ignorance of the vocabulary of the underlying information system holding the data. The intelligent interface is driven by means of appropriate automated reasoning techniques over an ontology describing the domain of the data in the information system. The output is a query which may be expressed in Datalog, SPARQL, or SQL.
The formal framework defines what a query is and how it is internally represented, which operations are available to the user in order to modify the query and how contextual feedback is provided about it presenting only relevant pieces of information.
The elements that constitute the query interface available to the user, providing visual access to the underlying reasoning services and operations for query manipulation, are precisely defined in their function by the framework.
The Quelo tool provides suitable a representation of the query interface in “linear form”, which is materialised in natural language.
Context
Recent research showed that adopting formal ontologies as a means for accessing
heterogeneous data sources has many benefits, in that not only does it provide
a uniform and flexible approach to integrating and describing such sources, but
it can also support the final user in querying them, thus improving the
usability of the integrated system.
We introduce a framework that enables access to heterogeneous data sources by
means of a conceptual schema and supports the users in the task of formulating
a precise query over it. In describing a specific domain, the ontology defines
a vocabulary which is often richer than the logical schema of the underlying
data and usually closer to the user's own vocabulary. The ontology can thus be
effectively exploited by the user in order to formulate a query that best
captures their information need. The user is constantly guided and assisted in
this task by an intuitive visual interface, whose intelligence is dynamically
driven by reasoning over the ontology. The inferences drawn on the conceptual
schema help the user in choosing what is more appropriate with respect to their
information need, restricting the possible choices to only those parts of the
ontology which are relevant and meaningful in a given context.
The most powerful and innovative feature of our framework lies in the fact that
not only do not users need to be aware of the underlying organisation of the
data, but they are also not required to have any specific knowledge of the
vocabulary used in the ontology. In fact, such knowledge can be gradually
acquired by using the tool itself, gaining confidence with both the vocabulary
and the ontology. Users may also decide to just explore the ontology without
actually querying the information system, with the aim of discovering general
information about the modelled domain.
Another important aspect is that only queries that are logically consistent
with the context and the constraints imposed by the ontology can be formulated,
since contradictory or redundant pieces of information are not presented to the
user at all. This makes user's choices clearer and simpler, by ruling out
irrelevant information that might be distracting and even generate confusion.
Furthermore, it also eliminates the often frustrating and time-consuming
process of finding the right combination of parts that together constitute a
meaningful query. For this reason, the user is free to explore the ontology
without the worry of making a wrong choice at some point and can thus
concentrate on expressing their information need at best.
Queries can be specified through a refinement process consisting in the
iteration of few basic operations: the user first specifies an initial request
starting with generic terms, then refines or deletes some of the previously
added terms or introduces new ones, and iterates the process until the
resulting query satisfies their information need. The available operations on
the current query include addition, substitution and deletion of pieces of
information, and all of them are supported by the reasoning services running
over the ontology.
Quelo relies on a web-based client-server architecture consisting
of three components:
- the tool logic, responsible of reasoning over the ontology
in order to provide only relevant information w.r.t. the current query;
- the natural language generation (NLG) engine, that given a query and a
lexicalisation map for the ontology produces an English sentence; the lexicon is automatically generated from the ontology;
- the user interface (GUI), that provides visual access to the query and
editing facilities for it, allowing to interact with the reasoning sub-system
while benefiting from the services of the NLG engine.
Online Tool
References
- Tiziana Catarci, Tania Di Mascio, Enrico Franconi, Giuseppe Santucci, and Sergio Tessaris. An ontology based visual tool for query formulation support. In Tari Z. Meersman R., editor, On The Move to Meaningful Internet Systems 2003: OTM 2003 Workshops, volume 2889 of Lecture Notes in Computer Science, pages 32-33. Springer, 2003.
- Tiziana Catarci, Paolo Dongilli, Tania Di Mascio, Enrico Franconi, Giuseppe Santucci, and Sergio Tessaris. An ontology based visual tool for query formulation support. In Proc. of the 16th Eur. Conf. on Artificial Intelligence (ECAI 2004), pages 308-312. IOS Press, 2004.
- Paolo Dongilli, Enrico Franconi, and Sergio Tessaris. Semantics driven support for query formulation. In Proc. of the 2004 Description Logic Workshop (DL 2004), 2004.
- Tiziana Catarci, Paolo Dongilli, Tania Di Mascio, Enrico Franconi, Giuseppe Santucci, and Sergio Tessaris. Usability evaluation tests in the SeWAsIE (SEmantic Webs and AgentS in Integrated Economies) project. In Proceedings of the 11th International Conference on Human-Computer Interaction (HCII 2005), 2005.
- T. Catarci, T. Di Mascio, P. Dongilli, E. Franconi, G. Santucci, and S. Tessaris. An ontology-based query manager: Usability evaluation. HCItaly2005 [16], pages 95-100, 2005.
- Tiziana Catarci, Tania Di Mascio, Paolo Dongilli, Enrico Franconi, Giuseppe Santucci, and Sergio Tessaris. SEWASIE (semantic web and agents in integrated economies) project: Usability evaluation tests. In Proceedings of the 4th Italian Symposium on Human-Computer Interaction (HCITALY 2005), Rome, Italy, September 2005.
- Paolo Dongilli, Pablo Fillottrani, Enrico Franconi, and Sergio Tessaris. A multi-agent system for querying heterogeneous data sources with ontologies. In Proceedings of Thirteenth Italian Symposium on Advanced Database Systems (SEBD-2005), Brixen-Bressanone, Italy, June 2005.
- Paolo Dongilli and Enrico Franconi. An Intelligent Query Interface with Natural Language Support. In Proc. of the 19th Int. Florida Artificial Intelligence Research Society Conference (FLAIRS 2006), Melbourne Beach, Florida, USA, May 2006.
- Paolo Dongilli. Natural Language Generation Applied to Intelligent Query Interfaces. PhD Thesis, 2008.
- Paolo Guagliardo. Theoretical Foundations of an Ontology-Based Visual Tool for Query Formulation Support. MSc Thesis, 2009.
- Marco Trevisan. A Portable Menu-guided Natural Language Interface to Knowledge Bases. MSc Thesis, 2009.
- Laura Haide Perez. Intelligent query interface: adding natural language support. KRDB Technical Report n. KRDB09-7, 2009.
- Enrico Franconi, Paolo Guagliardo, and Marco Trevisan. An intelligent query interface based on ontology navigation. In Proc. of the Workshop on Visual Interfaces to the Social and Semantic Web (VISSW 2010), February 2010.
- Enrico Franconi, Paolo Guagliardo, and Marco Trevisan. Quelo: a NL-based intelligent query interface. In Proc. of the 2nd Workshop on Controlled Natural Languages (CNL-2010), 2010.
- E. Franconi, P. Guagliardo, S. Tessaris, and M. Trevisan. A natural language ontology-driven query interface. In 9th International Conference on Terminology and Artificial Intelligence, 2011.
- [BASIC REFERENCE] Enrico Franconi, Paolo Guagliardo, Marco Trevisan, and Sergio Tessaris. Quelo: an ontology-driven query interface. In Proceedings of the 24th International Workshop on Description Logics (DL 2011), 2011.
- Enrico Franconi, Paolo Guagliardo, and Sergio Tessaris. Quelo at the IESD challenge 2012. In International Workshop on Intelligent Exploration of Semantic Data (IESD'2012), 2012.
- Laura Perez-Beltrachini, Claire Gardent, and Enrico Franconi. Incremental query generation. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), pages 183-191, 2014.
- Isabel Juárez-Castro. A Case Study on Intelligent Data Querying. MSc Thesis, 2015.
- Laura Perez-Beltrachini, Claire Gardent, Anselme Revuz, Saptarashmi Bandyopadhyay. Content selection as semantic-based ontology exploration. WebNLG 2016, pages 41-45, 2016.