Natural language interfaces to databases – an introduction

By Ion Androutsopoulos, Graeme D. Ritchie, Peter Thanisch. 1995

Abstract This paper is an introduction to natural language interfaces to databases (NLIDBS). A brief overview of the history of NLIDBS is first given. Some advantages and disadvantages of NLIDBS are then discussed, comparing NLIDBS to formal query languages, form-based interfaces, and graphical interfaces. An introduction to some of the linguistic problems NLIDBS have to confront follows, for the benefit of readers less familiar with computational linguistics. The discussion then moves on to NLIDB architectures, portability issues, restricted natural language input systems (including menu-based NLIDBS), and NLIDBS with reasoning capabilities. Some less explored areas of NLIDB research are then presented, namely database updates, meta-knowledge questions, temporal questions, and multi-modal NLIDBS. The paper ends with reflections on the current state of the art.

Subfields: Natural Language Processing, Question Answering & Reading Comprehension

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Question Answering & Reading Comprehension

Citations in the corpus

Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning (2017, background): “We investigate one particular aspect of NLI applied to relational databases: translating natural language questions to SQL queries.”
Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars (2005, background): “Androutsopoulos, Ritchie, and Thanisch (1995) provide a comprehensive summary of this work.”
Learning Dependency-Based Compositional Semantics (2011, neutral): “many others (see Androutsopoulos et al. (1995) for an overview).”
Compositional Semantic Parsing on Semi-Structured Tables (2015, background): “, 2011) usually cover a smaller scope of operations and compositionality, while early statistical semantic parsers for question answering (Wong and Mooney, 2007; Zettlemoyer and Collins, 2007) and high-accuracy natural language interfaces for databases (Androutsopoulos et al., 1995; Popescu et al., ”
Learning for Semantic Parsing with Statistical Machine Translation (2006, background): “Semantic parsing has found its way in practical applications such as natural-language (NL) interfaces to databases (Androutsopoulos et al., 1995) and advice taking (Kuhlmann et al., 2004).”
Neural Databases (2020, background): “There has been significant work on translating queries posed in natural language into SQL queries on a database whose schema is known [4, 23, 58], with extensions to semi-structured data and knowledge bases [7, 30].”
Optimising text quality in generation from relational databases (2000, background): “It should be clear that the task we are discussing is very distinct from the task of response generation in a natural language interface to a database (e.g., see Androutsopoulos et al. (1995)).”
Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback (2020, background): “However, early attempts in building NLIs to databases did not achieve the expected success due to limitations in language understanding capability, among other reasons (Androutsopoulos et al., 1995; Jones and Galliers, 1995).”
Bridging the Semantic Gap with SQL Query Logs in Natural Language Interfaces to Databases (2019, methodology): “Our work builds upon multiple streams of prior work: a) Natural language interfaces to databases (NLIDB): Research on NLIDBs extends as far back to the sixties and sev-enties [4], when interfaces were focused on solutions tailored to a speciﬁc domain.”
SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning (2017, background): “The study of translating natural language into SQL queries has a long history (Warren & Pereira, 1982; Androutsopoulos et al., 1993; 1995; Popescu et al., 2003; 2004; Li et al., 2006; Giordani & Moschitti, 2012; Zhang & Sun, 2013; Li & Jagadish, 2014; Wang et al., 2017).”
Constructing an Interactive Natural Language Interface for Relational Databases (2014, methodology): “Natural language interfaces to databases (NLIDB) have been studied for several decades [2].”
Programming With Unrestricted Natural Language (2005, background): “The most popular task is a Natural Language Interface for a Database (NLIDB) (Androutsopoulos et al., 1995).”
Eviza: A Natural Language Interface for Visual Analysis (2016, background): “Another early application for natural language input was to express database queries [11].”
Towards Ecologically Valid Research on Language User Interfaces (2020, unknown): “…developing language user interfaces was done by symbolic AI engineers, who analyzed the problem domain and designed linguistic rules for mapping utterances onto formal meaning representations (see, e.g., a survey of early language user interfaces to databases by Androutsopoulos et al. (1995)).”
SQLizer: query synthesis from natural language (2017, background): “The second line of work on query synthesis uses natural language descriptions to convey user intent [Androutsopoulos et al. 1993, 1995; Li and Jagadish 2014; Li et al. 2006; Popescu et al. 2004, 2003; Warren and Pereira 1982].”
Book Reviews: Ontology-Based Interpretation of Natural Language by Philipp Cimiano, Christina Unger and John McCrae (2014, unknown): “ONTOLOGY-BASED INTERPRETATIONFORQUESTIONANSWERING answering information needs with respect to databases [Androutsopoulos et al., 1995].”
Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions (2021, background): “Natural Language Interfaces to Databases The task of building natural language interfaces to database (NLIDB) has aroused great interest in both the NLP and DB communities since the 1970s (Warren and Pereira, 1981; Androutsopoulos et al., 1995; Popescu et al., 2004; Hallett, 2006; Giordani and Mosch”