HackerPapers

arXiv:cmp-lg/9503016cs.CL

Natural Language Interfaces to Databases - An Introduction

I. Androutsopoulos, G. D. Ritchie, P. Thanisch

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

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.

arXiv comments
50 pages, uuencoded compressed tar file, containing LaTeX code and .eps figures. Uses a4wide.sty. (No changes in the text. Fixed problem with epsf macro. Use the epsf.sty included in the tar file, not the epsf.sty of the cmp-lg server.)
Journal reference
Natural Language Engineering 1:1, 29-81
DOI
Subjects
cs.CLComputation and Language

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Jan 2024 to Jan 2024.

Comments linking this paper, per year.

Discussed in comments1 thread

    • Programmers have known for decades that it's very hard for people to express their requirements in prose, that's one reason why natural-language user interfaces have never lived up to the hype. Ambiguities stump computers. What does "List all employees in the company with a…

      cratermoonView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.