A natural language help system shell through functional programming

Robert Plant, Stephen Murrell

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper investigates the development of a natural language (NL) interface for mixed initiative dialogues within a constrained domain and demonstrates the applicability of the functional approach to NL system development. The system consists of two major components, a natural language subsystem comprises a general-purpose parser that interprets a 'plug and play' tagged BNF grammar (which may be ambiguous), to parse natural language input and extract semantic information. The knowledge-based subsystem uses the semantic tags extracted by the natural language subsystem to generate a focused query to select the most appropriate script for a guided dialogue with the user. The system was written entirely in a purely functional language, which resulted in a surprisingly small and simple program.

Original languageEnglish (US)
Pages (from-to)19-35
Number of pages17
JournalKnowledge-Based Systems
Volume18
Issue number1
DOIs
StatePublished - Feb 2005

Fingerprint

Functional programming
Semantics
Language
Programming
Shell
Subsystem

Keywords

  • Automated responses
  • Functional programming
  • Natural language processing
  • Scripts

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

A natural language help system shell through functional programming. / Plant, Robert; Murrell, Stephen.

In: Knowledge-Based Systems, Vol. 18, No. 1, 02.2005, p. 19-35.

Research output: Contribution to journalArticle

Plant, Robert ; Murrell, Stephen. / A natural language help system shell through functional programming. In: Knowledge-Based Systems. 2005 ; Vol. 18, No. 1. pp. 19-35.
@article{91d0696a587c43de89050350b1f696ef,
title = "A natural language help system shell through functional programming",
abstract = "This paper investigates the development of a natural language (NL) interface for mixed initiative dialogues within a constrained domain and demonstrates the applicability of the functional approach to NL system development. The system consists of two major components, a natural language subsystem comprises a general-purpose parser that interprets a 'plug and play' tagged BNF grammar (which may be ambiguous), to parse natural language input and extract semantic information. The knowledge-based subsystem uses the semantic tags extracted by the natural language subsystem to generate a focused query to select the most appropriate script for a guided dialogue with the user. The system was written entirely in a purely functional language, which resulted in a surprisingly small and simple program.",
keywords = "Automated responses, Functional programming, Natural language processing, Scripts",
author = "Robert Plant and Stephen Murrell",
year = "2005",
month = "2",
doi = "10.1016/j.knosys.2004.04.002",
language = "English (US)",
volume = "18",
pages = "19--35",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - A natural language help system shell through functional programming

AU - Plant, Robert

AU - Murrell, Stephen

PY - 2005/2

Y1 - 2005/2

N2 - This paper investigates the development of a natural language (NL) interface for mixed initiative dialogues within a constrained domain and demonstrates the applicability of the functional approach to NL system development. The system consists of two major components, a natural language subsystem comprises a general-purpose parser that interprets a 'plug and play' tagged BNF grammar (which may be ambiguous), to parse natural language input and extract semantic information. The knowledge-based subsystem uses the semantic tags extracted by the natural language subsystem to generate a focused query to select the most appropriate script for a guided dialogue with the user. The system was written entirely in a purely functional language, which resulted in a surprisingly small and simple program.

AB - This paper investigates the development of a natural language (NL) interface for mixed initiative dialogues within a constrained domain and demonstrates the applicability of the functional approach to NL system development. The system consists of two major components, a natural language subsystem comprises a general-purpose parser that interprets a 'plug and play' tagged BNF grammar (which may be ambiguous), to parse natural language input and extract semantic information. The knowledge-based subsystem uses the semantic tags extracted by the natural language subsystem to generate a focused query to select the most appropriate script for a guided dialogue with the user. The system was written entirely in a purely functional language, which resulted in a surprisingly small and simple program.

KW - Automated responses

KW - Functional programming

KW - Natural language processing

KW - Scripts

UR - http://www.scopus.com/inward/record.url?scp=13944278539&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13944278539&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2004.04.002

DO - 10.1016/j.knosys.2004.04.002

M3 - Article

AN - SCOPUS:13944278539

VL - 18

SP - 19

EP - 35

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

IS - 1

ER -