A Portable Natural Language Interface for Diverse Databases Using Ontologies

Zárate, Antonio; Pazos, Rodolfo; Gelbukh, Alexander; Padrón, Isabel

doi:10.1007/3-540-36456-0_52

Cited by 7 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dictionaries used by existing NLIDBs are created manually or semi-automatically [2]. We suggest automatic generation of the domain dictionary from a synonym dictionary and the database metadata with the help of some linguistic processing.…”

Section: Generation Of the Domain Dictionarymentioning

confidence: 99%

A Domain Independent Natural Language Interface to Databases Capable of Processing Complex Queries

Rangel

Pérez

Gonzalez

et al. 2005

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. We present a method for creating natural language interfaces to databases (NLIDB) that allow for translating natural language queries into SQL. The method is domain independent, i.e., it avoids the tedious process of configuring the NLIDB for a given domain. We automatically generate the domain dictionary for query translation using semantic metadata of the database. Our semantic representation of a query is a graph including information from database metadata. The query is translated taking into account the parts of speech of its words (obtained with some linguistic processing). Specifically, unlike most existing NLIDBs, we take seriously auxiliary words (prepositions and conjunctions) as set theory operators, which allows for processing more complex queries. Experimental results (conducted on two Spanish databases from different domains) show that treatment of auxiliary words improves correctness of translation by 12.1%. With the developed NLIDB 82of queries were correctly translated (and thus answered). Reconfiguring the NLIDB from one domain to the other took only ten minutes.

show abstract

Section: Generation Of the Domain Dictionarymentioning

confidence: 99%

A Domain Independent Natural Language Interface to Databases Capable of Processing Complex Queries

Rangel

Pérez

Gonzalez

et al. 2005

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…A cost-benefit analysis gives insight into the implications of implementing the recommendations of a software quality model in the context of a dynamic development process [3]. Logistic regression in conjunction with a specialized mathematical model, which we have been proposed, predicted whether each module was fault-prone or not [4].…”

Section: Introductionmentioning

confidence: 99%

Return on Investment and Effort Expenditure in the Software Development Environment

KumarSaini¹,

Ahmad²

2012

IJAIS

View full text Add to dashboard Cite

Software development is tedious, expensive and requires lot of resources and investment. Justification of the resources and investments are highly required in the software industry. Development of reliable and quality software has become increasingly important in today's world. A static model of the software development life cycle that treats all modules similarly is becoming inadequate to the task. In this paper efforts are made to quantify the concept of return on investment and factors responsible for improving the return on investment. In the second part of the paper, we are trying to justify the effort expenditure and how to optimize the effort expenditure.

show abstract

“…The customization methodology proposed for an NLIDB [16] is composed of the following stages: analysis of the database semantic; obtaining a query corpus from potential users; classification of this corpus in categories (similar to the ones defined in [4]) whose definition is linked with a relationship; definition of useful concepts to answer queries; identification of relations and concepts in the knowledge base; and connecting query elements with concepts and relations that explain the database semantics.…”

Section: Customization Methodologymentioning

confidence: 99%

Improving the Customization of Natural Language Interface to Databases Using an Ontology

Zarate

Pazos

Gelbukh

et al.

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Natural language interfaces to databases are considered one of the best alternatives for final users who wish to make complex, uncommon and frequent queries, which is a very common need in organizations. The use of this type of interfaces has been very limited, due to their limited publicizing and the complexity to adapt them to users' needs, and because their precision varies widely. We propose as a solution to the problem of customizing this type of interfaces, the use of an ontology as a knowledge base whose design is simple and flexible enough to make the use and acceptance of these interfaces more accessible. This paper describes the design of the ontology, as well as a series of comparative evaluations of this approach versus the customization process of a commercial interface. This evaluation aims at assessing the acceptance of this approach by of those that will potentially customize the interface to a database, in contrast to the precision tests that are commonly applied to this type of interfaces. In spite of the difficulties found to carry out the evaluations, the results show that the use of our approach is preferred as a natural language interface customization means to the process of the most popular commercial interface. The estimations indicate that the potential people on charge of the process of customization of this type of interfaces considers that using the ontology as interface knowledge base would allow to answer a wider diversity of types of queries than those that would allow to answer a commercial interface.

show abstract

A Portable Natural Language Interface for Diverse Databases Using Ontologies

Cited by 7 publications

References 2 publications

A Domain Independent Natural Language Interface to Databases Capable of Processing Complex Queries

A Domain Independent Natural Language Interface to Databases Capable of Processing Complex Queries

Return on Investment and Effort Expenditure in the Software Development Environment

Improving the Customization of Natural Language Interface to Databases Using an Ontology

Contact Info

Product

Resources

About